diff --git a/.dockerignore b/.dockerignore old mode 100755 new mode 100644 diff --git a/.gitattributes b/.gitattributes old mode 100755 new mode 100644 diff --git a/.github/ISSUE_TEMPLATE/10_bug_report.yml b/.github/ISSUE_TEMPLATE/10_bug_report.yml old mode 100755 new mode 100644 diff --git a/.github/ISSUE_TEMPLATE/20_feature_request.md b/.github/ISSUE_TEMPLATE/20_feature_request.md old mode 100755 new mode 100644 diff --git a/.github/ISSUE_TEMPLATE/30_model_request.md b/.github/ISSUE_TEMPLATE/30_model_request.md old mode 100755 new mode 100644 diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml old mode 100755 new mode 100644 diff --git a/.github/workflows/latest.yaml b/.github/workflows/latest.yaml old mode 100755 new mode 100644 diff --git a/.github/workflows/release.yaml b/.github/workflows/release.yaml old mode 100755 new mode 100644 diff --git a/.github/workflows/test.yaml b/.github/workflows/test.yaml old mode 100755 new mode 100644 diff --git a/.gitignore b/.gitignore old mode 100755 new mode 100644 diff --git a/.gitmodules b/.gitmodules old mode 100755 new mode 100644 diff --git a/.golangci.yaml b/.golangci.yaml old mode 100755 new mode 100644 diff --git a/.prettierrc.json b/.prettierrc.json old mode 100755 new mode 100644 diff --git a/Dockerfile b/Dockerfile old mode 100755 new mode 100644 diff --git a/LICENSE b/LICENSE old mode 100755 new mode 100644 diff --git a/README copy.md b/README copy.md new file mode 100644 index 0000000000000000000000000000000000000000..235de75a09a7f4cfa6ae2a79651f00a409ef45da --- /dev/null +++ b/README copy.md @@ -0,0 +1,71 @@ +#
Ollama
+ +## 简介 + +1 Ollama是以llama.cpp为后端的前端大模型推理框架，可快速部署主流模型。 + +## 安装 + +### 1、使用dockerfile方式安装 + +直接下载本仓库中的`v0.3.5`分支，然后执行`docker build xxxxx`相关命令（具体需自行查阅相关资料）。 + +如遇到卡数检测错误，请参考 https://developer.hpccube.com/codes/OpenDAS/ollama/-/issues/1 ，也可以提前进行修复。 + +### 2、使用源码编译方式安装（推荐） + +#### 环境准备 + +##### Docker + + docker pull docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-py3.10-dtk24.04.3-ubuntu20.04 + + docker run -i -t -d --device=/dev/kfd --privileged --network=host --device=/dev/dri --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home -v /opt/hyhal:/opt/hyhal:ro -v --group-add video --shm-size 16G --name {容器名} {镜像ID} + + +1、下载源码 + + git clone -b v0.3.5 http://developer.sourcefind.cn/codes/OpenDAS/ollama.git --depth=1 + cd ollama + +2、安装依赖包 + + cd llm/llama.cpp + pip install -r requirements.txt + +#### 编译 + +##### 环境设置 + export AMDGPU_TARGETS=当前设备型号（如：gfx906，gfx928等） + export HSA_OVERRIDE_GFX_VERSION=设备型号（如: gfx906对应9.0.6；gfx928对应9.2.8） + export LIBRARY_PATH=/opt/dtk/llvm/lib/clang/15.0.0/lib/linux/:$LIBRARY_PATH + export HIP_VISIBLE_DEVICES=所有设备号（0,1,2,3,4,5,6,...）/选择设备号 + +安装go + + cd ../.. + tar -C /usr/local -xzf go1.22.3.linux-amd64.tar.gz + export PATH=$PATH:/usr/local/go/bin + + # 修改go下载源，提升速度（按需设置） + go env -w GO111MODULE=on + go env -w GOPROXY=https://goproxy.cn,direct + +##### 运行编译 + + cd llm/generate && bash gen_linux.sh + cd ../.. && go build + +## 验证 + + ./ollama serve （选择可用设备，可通过上条命令输出结果查看） + ./ollama run llama3.1 + +更多使用方式请参考[原项目](https://github.com/ollama/ollama)。 + +注意：每次运行前请检查环境变量`HSA_OVERRIDE_GFX_VERSION`是否正确设置。 + +## 参考资料 + +* https://github.com/ollama/ollama +* https://github.com/ggerganov/llama.cpp diff --git a/README.md b/README.md index 235de75a09a7f4cfa6ae2a79651f00a409ef45da..aae92e6c2a841b26eb08f83d808f828f22a9944c 100644 --- a/README.md +++ b/README.md @@ -1,71 +1,409 @@ -#
Ollama
+
+ ollama +
-## 简介 +# Ollama -1 Ollama是以llama.cpp为后端的前端大模型推理框架，可快速部署主流模型。 +[![Discord](https://dcbadge.vercel.app/api/server/ollama?style=flat&compact=true)](https://discord.gg/ollama) -## 安装 +Get up and running with large language models. -### 1、使用dockerfile方式安装 +### macOS -直接下载本仓库中的`v0.3.5`分支，然后执行`docker build xxxxx`相关命令（具体需自行查阅相关资料）。 +[Download](https://ollama.com/download/Ollama-darwin.zip) -如遇到卡数检测错误，请参考 https://developer.hpccube.com/codes/OpenDAS/ollama/-/issues/1 ，也可以提前进行修复。 +### Windows preview -### 2、使用源码编译方式安装（推荐） +[Download](https://ollama.com/download/OllamaSetup.exe) -#### 环境准备 +### Linux -##### Docker +``` +curl -fsSL https://ollama.com/install.sh | sh +``` - docker pull docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.1.0-py3.10-dtk24.04.3-ubuntu20.04 - - docker run -i -t -d --device=/dev/kfd --privileged --network=host --device=/dev/dri --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v 项目地址(绝对路径):/home -v /opt/hyhal:/opt/hyhal:ro -v --group-add video --shm-size 16G --name {容器名} {镜像ID} +[Manual install instructions](https://github.com/ollama/ollama/blob/main/docs/linux.md) +### Docker -1、下载源码 +The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `ollama/ollama` is available on Docker Hub. - git clone -b v0.3.5 http://developer.sourcefind.cn/codes/OpenDAS/ollama.git --depth=1 - cd ollama +### Libraries -2、安装依赖包 +- [ollama-python](https://github.com/ollama/ollama-python) +- [ollama-js](https://github.com/ollama/ollama-js) - cd llm/llama.cpp - pip install -r requirements.txt +## Quickstart -#### 编译 +To run and chat with [Llama 3.1](https://ollama.com/library/llama3.1): -##### 环境设置 - export AMDGPU_TARGETS=当前设备型号（如：gfx906，gfx928等） - export HSA_OVERRIDE_GFX_VERSION=设备型号（如: gfx906对应9.0.6；gfx928对应9.2.8） - export LIBRARY_PATH=/opt/dtk/llvm/lib/clang/15.0.0/lib/linux/:$LIBRARY_PATH - export HIP_VISIBLE_DEVICES=所有设备号（0,1,2,3,4,5,6,...）/选择设备号 +``` +ollama run llama3.1 +``` -安装go +## Model library - cd ../.. - tar -C /usr/local -xzf go1.22.3.linux-amd64.tar.gz - export PATH=$PATH:/usr/local/go/bin - - # 修改go下载源，提升速度（按需设置） - go env -w GO111MODULE=on - go env -w GOPROXY=https://goproxy.cn,direct +Ollama supports a list of models available on [ollama.com/library](https://ollama.com/library 'ollama model library') -##### 运行编译 +Here are some example models that can be downloaded: - cd llm/generate && bash gen_linux.sh - cd ../.. && go build +| Model | Parameters | Size | Download | +| ------------------ | ---------- | ----- | ------------------------------ | +| Llama 3.1 | 8B | 4.7GB | `ollama run llama3.1` | +| Llama 3.1 | 70B | 40GB | `ollama run llama3.1:70b` | +| Llama 3.1 | 405B | 231GB | `ollama run llama3.1:405b` | +| Phi 3 Mini | 3.8B | 2.3GB | `ollama run phi3` | +| Phi 3 Medium | 14B | 7.9GB | `ollama run phi3:medium` | +| Gemma 2 | 2B | 1.6GB | `ollama run gemma2:2b` | +| Gemma 2 | 9B | 5.5GB | `ollama run gemma2` | +| Gemma 2 | 27B | 16GB | `ollama run gemma2:27b` | +| Mistral | 7B | 4.1GB | `ollama run mistral` | +| Moondream 2 | 1.4B | 829MB | `ollama run moondream` | +| Neural Chat | 7B | 4.1GB | `ollama run neural-chat` | +| Starling | 7B | 4.1GB | `ollama run starling-lm` | +| Code Llama | 7B | 3.8GB | `ollama run codellama` | +| Llama 2 Uncensored | 7B | 3.8GB | `ollama run llama2-uncensored` | +| LLaVA | 7B | 4.5GB | `ollama run llava` | +| Solar | 10.7B | 6.1GB | `ollama run solar` | -## 验证 +> [!NOTE] +> You should have at least 8 GB of RAM available to run the 7B models, 16 GB to run the 13B models, and 32 GB to run the 33B models. - ./ollama serve （选择可用设备，可通过上条命令输出结果查看） - ./ollama run llama3.1 +## Customize a model -更多使用方式请参考[原项目](https://github.com/ollama/ollama)。 +### Import from GGUF -注意：每次运行前请检查环境变量`HSA_OVERRIDE_GFX_VERSION`是否正确设置。 +Ollama supports importing GGUF models in the Modelfile: -## 参考资料 +1. Create a file named `Modelfile`, with a `FROM` instruction with the local filepath to the model you want to import. + + ``` + FROM ./vicuna-33b.Q4_0.gguf + ``` + +2. Create the model in Ollama + + ``` + ollama create example -f Modelfile + ``` + +3. Run the model + + ``` + ollama run example + ``` + +### Import from PyTorch or Safetensors + +See the [guide](docs/import.md) on importing models for more information. + +### Customize a prompt + +Models from the Ollama library can be customized with a prompt. For example, to customize the `llama3.1` model: + +``` +ollama pull llama3.1 +``` + +Create a `Modelfile`: + +``` +FROM llama3.1 + +# set the temperature to 1 [higher is more creative, lower is more coherent] +PARAMETER temperature 1 + +# set the system message +SYSTEM """ +You are Mario from Super Mario Bros. Answer as Mario, the assistant, only. +""" +``` + +Next, create and run the model: + +``` +ollama create mario -f ./Modelfile +ollama run mario +>>> hi +Hello! It's your friend Mario. +``` + +For more examples, see the [examples](examples) directory. For more information on working with a Modelfile, see the [Modelfile](docs/modelfile.md) documentation. + +## CLI Reference + +### Create a model + +`ollama create` is used to create a model from a Modelfile. + +``` +ollama create mymodel -f ./Modelfile +``` + +### Pull a model + +``` +ollama pull llama3.1 +``` + +> This command can also be used to update a local model. Only the diff will be pulled. + +### Remove a model + +``` +ollama rm llama3.1 +``` + +### Copy a model + +``` +ollama cp llama3.1 my-model +``` + +### Multiline input + +For multiline input, you can wrap text with `"""`: + +``` +>>> """Hello, +... world! +... """ +I'm a basic program that prints the famous "Hello, world!" message to the console. +``` + +### Multimodal models + +``` +ollama run llava "What's in this image? /Users/jmorgan/Desktop/smile.png" +The image features a yellow smiley face, which is likely the central focus of the picture. +``` + +### Pass the prompt as an argument + +``` +$ ollama run llama3.1 "Summarize this file: $(cat README.md)" + Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications. +``` + +### Show model information + +``` +ollama show llama3.1 +``` + +### List models on your computer + +``` +ollama list +``` + +### Start Ollama + +`ollama serve` is used when you want to start ollama without running the desktop application. + +## Building + +See the [developer guide](https://github.com/ollama/ollama/blob/main/docs/development.md) + +### Running local builds + +Next, start the server: + +``` +./ollama serve +``` + +Finally, in a separate shell, run a model: + +``` +./ollama run llama3.1 +``` + +## REST API + +Ollama has a REST API for running and managing models. + +### Generate a response + +``` +curl http://localhost:11434/api/generate -d '{ + "model": "llama3.1", + "prompt":"Why is the sky blue?" +}' +``` + +### Chat with a model + +``` +curl http://localhost:11434/api/chat -d '{ + "model": "llama3.1", + "messages": [ + { "role": "user", "content": "why is the sky blue?" } + ] +}' +``` + +See the [API documentation](./docs/api.md) for all endpoints. + +## Community Integrations + +### Web & Desktop + +- [Open WebUI](https://github.com/open-webui/open-webui) +- [Enchanted (macOS native)](https://github.com/AugustDev/enchanted) +- [Hollama](https://github.com/fmaclen/hollama) +- [Lollms-Webui](https://github.com/ParisNeo/lollms-webui) +- [LibreChat](https://github.com/danny-avila/LibreChat) +- [Bionic GPT](https://github.com/bionic-gpt/bionic-gpt) +- [HTML UI](https://github.com/rtcfirefly/ollama-ui) +- [Saddle](https://github.com/jikkuatwork/saddle) +- [Chatbot UI](https://github.com/ivanfioravanti/chatbot-ollama) +- [Chatbot UI v2](https://github.com/mckaywrigley/chatbot-ui) +- [Typescript UI](https://github.com/ollama-interface/Ollama-Gui?tab=readme-ov-file) +- [Minimalistic React UI for Ollama Models](https://github.com/richawo/minimal-llm-ui) +- [Ollamac](https://github.com/kevinhermawan/Ollamac) +- [big-AGI](https://github.com/enricoros/big-AGI/blob/main/docs/config-local-ollama.md) +- [Cheshire Cat assistant framework](https://github.com/cheshire-cat-ai/core) +- [Amica](https://github.com/semperai/amica) +- [chatd](https://github.com/BruceMacD/chatd) +- [Ollama-SwiftUI](https://github.com/kghandour/Ollama-SwiftUI) +- [Dify.AI](https://github.com/langgenius/dify) +- [MindMac](https://mindmac.app) +- [NextJS Web Interface for Ollama](https://github.com/jakobhoeg/nextjs-ollama-llm-ui) +- [Msty](https://msty.app) +- [Chatbox](https://github.com/Bin-Huang/Chatbox) +- [WinForm Ollama Copilot](https://github.com/tgraupmann/WinForm_Ollama_Copilot) +- [NextChat](https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web) with [Get Started Doc](https://docs.nextchat.dev/models/ollama) +- [Alpaca WebUI](https://github.com/mmo80/alpaca-webui) +- [OllamaGUI](https://github.com/enoch1118/ollamaGUI) +- [OpenAOE](https://github.com/InternLM/OpenAOE) +- [Odin Runes](https://github.com/leonid20000/OdinRunes) +- [LLM-X](https://github.com/mrdjohnson/llm-x) (Progressive Web App) +- [AnythingLLM (Docker + MacOs/Windows/Linux native app)](https://github.com/Mintplex-Labs/anything-llm) +- [Ollama Basic Chat: Uses HyperDiv Reactive UI](https://github.com/rapidarchitect/ollama_basic_chat) +- [Ollama-chats RPG](https://github.com/drazdra/ollama-chats) +- [QA-Pilot](https://github.com/reid41/QA-Pilot) (Chat with Code Repository) +- [ChatOllama](https://github.com/sugarforever/chat-ollama) (Open Source Chatbot based on Ollama with Knowledge Bases) +- [CRAG Ollama Chat](https://github.com/Nagi-ovo/CRAG-Ollama-Chat) (Simple Web Search with Corrective RAG) +- [RAGFlow](https://github.com/infiniflow/ragflow) (Open-source Retrieval-Augmented Generation engine based on deep document understanding) +- [StreamDeploy](https://github.com/StreamDeploy-DevRel/streamdeploy-llm-app-scaffold) (LLM Application Scaffold) +- [chat](https://github.com/swuecho/chat) (chat web app for teams) +- [Lobe Chat](https://github.com/lobehub/lobe-chat) with [Integrating Doc](https://lobehub.com/docs/self-hosting/examples/ollama) +- [Ollama RAG Chatbot](https://github.com/datvodinh/rag-chatbot.git) (Local Chat with multiple PDFs using Ollama and RAG) +- [BrainSoup](https://www.nurgo-software.com/products/brainsoup) (Flexible native client with RAG & multi-agent automation) +- [macai](https://github.com/Renset/macai) (macOS client for Ollama, ChatGPT, and other compatible API back-ends) +- [Olpaka](https://github.com/Otacon/olpaka) (User-friendly Flutter Web App for Ollama) +- [OllamaSpring](https://github.com/CrazyNeil/OllamaSpring) (Ollama Client for macOS) +- [LLocal.in](https://github.com/kartikm7/llocal) (Easy to use Electron Desktop Client for Ollama) +- [Ollama with Google Mesop](https://github.com/rapidarchitect/ollama_mesop/) (Mesop Chat Client implementation with Ollama) +- [Kerlig AI](https://www.kerlig.com/) (AI writing assistant for macOS) +- [AI Studio](https://github.com/MindWorkAI/AI-Studio) +- [Sidellama](https://github.com/gyopak/sidellama) (browser-based LLM client) +- [LLMStack](https://github.com/trypromptly/LLMStack) (No-code multi-agent framework to build LLM agents and workflows) +- [BoltAI for Mac](https://boltai.com) (AI Chat Client for Mac) +- [Harbor](https://github.com/av/harbor) (Containerized LLM Toolkit with Ollama as default backend) + +### Terminal + +- [oterm](https://github.com/ggozad/oterm) +- [Ellama Emacs client](https://github.com/s-kostyaev/ellama) +- [Emacs client](https://github.com/zweifisch/ollama) +- [gen.nvim](https://github.com/David-Kunz/gen.nvim) +- [ollama.nvim](https://github.com/nomnivore/ollama.nvim) +- [ollero.nvim](https://github.com/marco-souza/ollero.nvim) +- [ollama-chat.nvim](https://github.com/gerazov/ollama-chat.nvim) +- [ogpt.nvim](https://github.com/huynle/ogpt.nvim) +- [gptel Emacs client](https://github.com/karthink/gptel) +- [Oatmeal](https://github.com/dustinblackman/oatmeal) +- [cmdh](https://github.com/pgibler/cmdh) +- [ooo](https://github.com/npahlfer/ooo) +- [shell-pilot](https://github.com/reid41/shell-pilot) +- [tenere](https://github.com/pythops/tenere) +- [llm-ollama](https://github.com/taketwo/llm-ollama) for [Datasette's LLM CLI](https://llm.datasette.io/en/stable/). +- [typechat-cli](https://github.com/anaisbetts/typechat-cli) +- [ShellOracle](https://github.com/djcopley/ShellOracle) +- [tlm](https://github.com/yusufcanb/tlm) +- [podman-ollama](https://github.com/ericcurtin/podman-ollama) +- [gollama](https://github.com/sammcj/gollama) +- [Ollama eBook Summary](https://github.com/cognitivetech/ollama-ebook-summary/) + +### Database + +- [MindsDB](https://github.com/mindsdb/mindsdb/blob/staging/mindsdb/integrations/handlers/ollama_handler/README.md) (Connects Ollama models with nearly 200 data platforms and apps) +- [chromem-go](https://github.com/philippgille/chromem-go/blob/v0.5.0/embed_ollama.go) with [example](https://github.com/philippgille/chromem-go/tree/v0.5.0/examples/rag-wikipedia-ollama) + +### Package managers + +- [Pacman](https://archlinux.org/packages/extra/x86_64/ollama/) +- [Helm Chart](https://artifacthub.io/packages/helm/ollama-helm/ollama) +- [Guix channel](https://codeberg.org/tusharhero/ollama-guix) + +### Libraries + +- [LangChain](https://python.langchain.com/docs/integrations/llms/ollama) and [LangChain.js](https://js.langchain.com/docs/modules/model_io/models/llms/integrations/ollama) with [example](https://js.langchain.com/docs/use_cases/question_answering/local_retrieval_qa) +- [Firebase Genkit](https://firebase.google.com/docs/genkit/plugins/ollama) +- [LangChainGo](https://github.com/tmc/langchaingo/) with [example](https://github.com/tmc/langchaingo/tree/main/examples/ollama-completion-example) +- [LangChain4j](https://github.com/langchain4j/langchain4j) with [example](https://github.com/langchain4j/langchain4j-examples/tree/main/ollama-examples/src/main/java) +- [LangChainRust](https://github.com/Abraxas-365/langchain-rust) with [example](https://github.com/Abraxas-365/langchain-rust/blob/main/examples/llm_ollama.rs) +- [LlamaIndex](https://gpt-index.readthedocs.io/en/stable/examples/llm/ollama.html) +- [LiteLLM](https://github.com/BerriAI/litellm) +- [OllamaSharp for .NET](https://github.com/awaescher/OllamaSharp) +- [Ollama for Ruby](https://github.com/gbaptista/ollama-ai) +- [Ollama-rs for Rust](https://github.com/pepperoni21/ollama-rs) +- [Ollama-hpp for C++](https://github.com/jmont-dev/ollama-hpp) +- [Ollama4j for Java](https://github.com/amithkoujalgi/ollama4j) +- [ModelFusion Typescript Library](https://modelfusion.dev/integration/model-provider/ollama) +- [OllamaKit for Swift](https://github.com/kevinhermawan/OllamaKit) +- [Ollama for Dart](https://github.com/breitburg/dart-ollama) +- [Ollama for Laravel](https://github.com/cloudstudio/ollama-laravel) +- [LangChainDart](https://github.com/davidmigloz/langchain_dart) +- [Semantic Kernel - Python](https://github.com/microsoft/semantic-kernel/tree/main/python/semantic_kernel/connectors/ai/ollama) +- [Haystack](https://github.com/deepset-ai/haystack-integrations/blob/main/integrations/ollama.md) +- [Elixir LangChain](https://github.com/brainlid/langchain) +- [Ollama for R - rollama](https://github.com/JBGruber/rollama) +- [Ollama for R - ollama-r](https://github.com/hauselin/ollama-r) +- [Ollama-ex for Elixir](https://github.com/lebrunel/ollama-ex) +- [Ollama Connector for SAP ABAP](https://github.com/b-tocs/abap_btocs_ollama) +- [Testcontainers](https://testcontainers.com/modules/ollama/) +- [Portkey](https://portkey.ai/docs/welcome/integration-guides/ollama) +- [PromptingTools.jl](https://github.com/svilupp/PromptingTools.jl) with an [example](https://svilupp.github.io/PromptingTools.jl/dev/examples/working_with_ollama) +- [LlamaScript](https://github.com/Project-Llama/llamascript) + +### Mobile + +- [Enchanted](https://github.com/AugustDev/enchanted) +- [Maid](https://github.com/Mobile-Artificial-Intelligence/maid) + +### Extensions & Plugins + +- [Raycast extension](https://github.com/MassimilianoPasquini97/raycast_ollama) +- [Discollama](https://github.com/mxyng/discollama) (Discord bot inside the Ollama discord channel) +- [Continue](https://github.com/continuedev/continue) +- [Obsidian Ollama plugin](https://github.com/hinterdupfinger/obsidian-ollama) +- [Logseq Ollama plugin](https://github.com/omagdy7/ollama-logseq) +- [NotesOllama](https://github.com/andersrex/notesollama) (Apple Notes Ollama plugin) +- [Dagger Chatbot](https://github.com/samalba/dagger-chatbot) +- [Discord AI Bot](https://github.com/mekb-turtle/discord-ai-bot) +- [Ollama Telegram Bot](https://github.com/ruecat/ollama-telegram) +- [Hass Ollama Conversation](https://github.com/ej52/hass-ollama-conversation) +- [Rivet plugin](https://github.com/abrenneke/rivet-plugin-ollama) +- [Obsidian BMO Chatbot plugin](https://github.com/longy2k/obsidian-bmo-chatbot) +- [Cliobot](https://github.com/herval/cliobot) (Telegram bot with Ollama support) +- [Copilot for Obsidian plugin](https://github.com/logancyang/obsidian-copilot) +- [Obsidian Local GPT plugin](https://github.com/pfrankov/obsidian-local-gpt) +- [Open Interpreter](https://docs.openinterpreter.com/language-model-setup/local-models/ollama) +- [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama) +- [Ollama Copilot](https://github.com/bernardo-bruning/ollama-copilot) (Proxy that allows you to use ollama as a copilot like Github copilot) +- [twinny](https://github.com/rjmacarthy/twinny) (Copilot and Copilot chat alternative using Ollama) +- [Wingman-AI](https://github.com/RussellCanfield/wingman-ai) (Copilot code and chat alternative using Ollama and Hugging Face) +- [Page Assist](https://github.com/n4ze3m/page-assist) (Chrome Extension) +- [AI Telegram Bot](https://github.com/tusharhero/aitelegrambot) (Telegram bot using Ollama in backend) +- [AI ST Completion](https://github.com/yaroslavyaroslav/OpenAI-sublime-text) (Sublime Text 4 AI assistant plugin with Ollama support) +- [Discord-Ollama Chat Bot](https://github.com/kevinthedang/discord-ollama) (Generalized TypeScript Discord Bot w/ Tuning Documentation) +- [Discord AI chat/moderation bot](https://github.com/rapmd73/Companion) Chat/moderation bot written in python. Uses Ollama to create personalities. +- [Headless Ollama](https://github.com/nischalj10/headless-ollama) (Scripts to automatically install ollama client & models on any OS for apps that depends on ollama server) + +### Supported backends + +- [llama.cpp](https://github.com/ggerganov/llama.cpp) project founded by Georgi Gerganov. -* https://github.com/ollama/ollama -* https://github.com/ggerganov/llama.cpp diff --git a/SECURITY.md b/SECURITY.md old mode 100755 new mode 100644 diff --git a/api/client.go b/api/client.go old mode 100755 new mode 100644 diff --git a/api/client_test.go b/api/client_test.go old mode 100755 new mode 100644 diff --git a/api/types.go b/api/types.go old mode 100755 new mode 100644 diff --git a/api/types_test.go b/api/types_test.go old mode 100755 new mode 100644 diff --git a/app/.gitignore b/app/.gitignore old mode 100755 new mode 100644 diff --git a/app/README.md b/app/README.md old mode 100755 new mode 100644 diff --git a/app/assets/app.ico b/app/assets/app.ico old mode 100755 new mode 100644 diff --git a/app/assets/assets.go b/app/assets/assets.go old mode 100755 new mode 100644 diff --git a/app/assets/setup.bmp b/app/assets/setup.bmp old mode 100755 new mode 100644 diff --git a/app/assets/tray.ico b/app/assets/tray.ico old mode 100755 new mode 100644 diff --git a/app/assets/tray_upgrade.ico b/app/assets/tray_upgrade.ico old mode 100755 new mode 100644 diff --git a/app/lifecycle/getstarted_nonwindows.go b/app/lifecycle/getstarted_nonwindows.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/getstarted_windows.go b/app/lifecycle/getstarted_windows.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/lifecycle.go b/app/lifecycle/lifecycle.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/logging.go b/app/lifecycle/logging.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/logging_nonwindows.go b/app/lifecycle/logging_nonwindows.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/logging_test.go b/app/lifecycle/logging_test.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/logging_windows.go b/app/lifecycle/logging_windows.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/paths.go b/app/lifecycle/paths.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/server.go b/app/lifecycle/server.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/server_unix.go b/app/lifecycle/server_unix.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/server_windows.go b/app/lifecycle/server_windows.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/updater.go b/app/lifecycle/updater.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/updater_nonwindows.go b/app/lifecycle/updater_nonwindows.go old mode 100755 new mode 100644 diff --git a/app/lifecycle/updater_windows.go b/app/lifecycle/updater_windows.go old mode 100755 new mode 100644 diff --git a/app/main.go b/app/main.go old mode 100755 new mode 100644 diff --git a/app/ollama.iss b/app/ollama.iss old mode 100755 new mode 100644 diff --git a/app/ollama.rc b/app/ollama.rc old mode 100755 new mode 100644 diff --git a/app/ollama_welcome.ps1 b/app/ollama_welcome.ps1 old mode 100755 new mode 100644 diff --git a/app/store/store.go b/app/store/store.go old mode 100755 new mode 100644 diff --git a/app/store/store_darwin.go b/app/store/store_darwin.go old mode 100755 new mode 100644 diff --git a/app/store/store_linux.go b/app/store/store_linux.go old mode 100755 new mode 100644 diff --git a/app/store/store_windows.go b/app/store/store_windows.go old mode 100755 new mode 100644 diff --git a/app/tray/commontray/types.go b/app/tray/commontray/types.go old mode 100755 new mode 100644 diff --git a/app/tray/tray.go b/app/tray/tray.go old mode 100755 new mode 100644 diff --git a/app/tray/tray_nonwindows.go b/app/tray/tray_nonwindows.go old mode 100755 new mode 100644 diff --git a/app/tray/tray_windows.go b/app/tray/tray_windows.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/eventloop.go b/app/tray/wintray/eventloop.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/menus.go b/app/tray/wintray/menus.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/messages.go b/app/tray/wintray/messages.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/notifyicon.go b/app/tray/wintray/notifyicon.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/tray.go b/app/tray/wintray/tray.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/w32api.go b/app/tray/wintray/w32api.go old mode 100755 new mode 100644 diff --git a/app/tray/wintray/winclass.go b/app/tray/wintray/winclass.go old mode 100755 new mode 100644 diff --git a/auth/auth.go b/auth/auth.go old mode 100755 new mode 100644 diff --git a/cmd/cmd.go b/cmd/cmd.go old mode 100755 new mode 100644 diff --git a/cmd/interactive.go b/cmd/interactive.go old mode 100755 new mode 100644 diff --git a/cmd/interactive_test.go b/cmd/interactive_test.go old mode 100755 new mode 100644 diff --git a/cmd/start.go b/cmd/start.go old mode 100755 new mode 100644 diff --git a/cmd/start_darwin.go b/cmd/start_darwin.go old mode 100755 new mode 100644 diff --git a/cmd/start_default.go b/cmd/start_default.go old mode 100755 new mode 100644 diff --git a/cmd/start_windows.go b/cmd/start_windows.go old mode 100755 new mode 100644 diff --git a/convert/convert.go b/convert/convert.go old mode 100755 new mode 100644 diff --git a/convert/convert_gemma.go b/convert/convert_gemma.go old mode 100755 new mode 100644 diff --git a/convert/convert_llama.go b/convert/convert_llama.go old mode 100755 new mode 100644 diff --git a/convert/convert_mixtral.go b/convert/convert_mixtral.go old mode 100755 new mode 100644 diff --git a/convert/convert_test.go b/convert/convert_test.go old mode 100755 new mode 100644 diff --git a/convert/fs.go b/convert/fs.go old mode 100755 new mode 100644 diff --git a/convert/reader.go b/convert/reader.go old mode 100755 new mode 100644 diff --git a/convert/reader_safetensors.go b/convert/reader_safetensors.go old mode 100755 new mode 100644 diff --git a/convert/reader_torch.go b/convert/reader_torch.go old mode 100755 new mode 100644 diff --git a/convert/sentencepiece/sentencepiece_model.pb.go b/convert/sentencepiece/sentencepiece_model.pb.go old mode 100755 new mode 100644 diff --git a/convert/sentencepiece_model.proto b/convert/sentencepiece_model.proto old mode 100755 new mode 100644 diff --git a/convert/testdata/Meta-Llama-3-8B-Instruct.json b/convert/testdata/Meta-Llama-3-8B-Instruct.json old mode 100755 new mode 100644 diff --git a/convert/testdata/Mistral-7B-Instruct-v0.2.json b/convert/testdata/Mistral-7B-Instruct-v0.2.json old mode 100755 new mode 100644 diff --git a/convert/testdata/Mixtral-8x7B-Instruct-v0.1.json b/convert/testdata/Mixtral-8x7B-Instruct-v0.1.json old mode 100755 new mode 100644 diff --git a/convert/testdata/gemma-2b-it.json b/convert/testdata/gemma-2b-it.json old mode 100755 new mode 100644 diff --git a/convert/tokenizer.go b/convert/tokenizer.go old mode 100755 new mode 100644 diff --git a/convert/tokenizer_spm.go b/convert/tokenizer_spm.go old mode 100755 new mode 100644 diff --git a/docs/README.md b/docs/README.md old mode 100755 new mode 100644 diff --git a/docs/api.md b/docs/api.md old mode 100755 new mode 100644 diff --git a/docs/development.md b/docs/development.md old mode 100755 new mode 100644 diff --git a/docs/docker.md b/docs/docker.md old mode 100755 new mode 100644 diff --git a/docs/faq.md b/docs/faq.md old mode 100755 new mode 100644 diff --git a/docs/gpu.md b/docs/gpu.md old mode 100755 new mode 100644 diff --git a/docs/import.md b/docs/import.md old mode 100755 new mode 100644 diff --git a/docs/linux.md b/docs/linux.md old mode 100755 new mode 100644 diff --git a/docs/modelfile.md b/docs/modelfile.md old mode 100755 new mode 100644 diff --git a/docs/openai.md b/docs/openai.md old mode 100755 new mode 100644 diff --git a/docs/template.md b/docs/template.md old mode 100755 new mode 100644 diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md old mode 100755 new mode 100644 diff --git a/docs/tutorials.md b/docs/tutorials.md old mode 100755 new mode 100644 diff --git a/docs/tutorials/fly-gpu.md b/docs/tutorials/fly-gpu.md old mode 100755 new mode 100644 diff --git a/docs/tutorials/langchainjs.md b/docs/tutorials/langchainjs.md old mode 100755 new mode 100644 diff --git a/docs/tutorials/langchainpy.md b/docs/tutorials/langchainpy.md old mode 100755 new mode 100644 diff --git a/docs/tutorials/nvidia-jetson.md b/docs/tutorials/nvidia-jetson.md old mode 100755 new mode 100644 diff --git a/docs/windows.md b/docs/windows.md old mode 100755 new mode 100644 diff --git a/envconfig/config.go b/envconfig/config.go old mode 100755 new mode 100644 diff --git a/envconfig/config_test.go b/envconfig/config_test.go old mode 100755 new mode 100644 diff --git a/examples/.gitignore b/examples/.gitignore old mode 100755 new mode 100644 diff --git a/examples/README.md b/examples/README.md old mode 100755 new mode 100644 diff --git a/examples/flyio/.gitignore b/examples/flyio/.gitignore old mode 100755 new mode 100644 diff --git a/examples/flyio/README.md b/examples/flyio/README.md old mode 100755 new mode 100644 diff --git a/examples/go-chat/main.go b/examples/go-chat/main.go old mode 100755 new mode 100644 diff --git a/examples/go-generate-streaming/main.go b/examples/go-generate-streaming/main.go old mode 100755 new mode 100644 diff --git a/examples/go-generate/main.go b/examples/go-generate/main.go old mode 100755 new mode 100644 diff --git a/examples/go-http-generate/main.go b/examples/go-http-generate/main.go old mode 100755 new mode 100644 diff --git a/examples/go-multimodal/main.go b/examples/go-multimodal/main.go old mode 100755 new mode 100644 diff --git a/examples/go-pull-progress/main.go b/examples/go-pull-progress/main.go old mode 100755 new mode 100644 diff --git a/examples/jupyter-notebook/README.md b/examples/jupyter-notebook/README.md old mode 100755 new mode 100644 diff --git a/examples/jupyter-notebook/ollama.ipynb b/examples/jupyter-notebook/ollama.ipynb old mode 100755 new mode 100644 diff --git a/examples/kubernetes/README.md b/examples/kubernetes/README.md old mode 100755 new mode 100644 diff --git a/examples/kubernetes/cpu.yaml b/examples/kubernetes/cpu.yaml old mode 100755 new mode 100644 diff --git a/examples/kubernetes/gpu.yaml b/examples/kubernetes/gpu.yaml old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-document/README.md b/examples/langchain-python-rag-document/README.md old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-document/main.py b/examples/langchain-python-rag-document/main.py old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-document/requirements.txt b/examples/langchain-python-rag-document/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/.gitignore b/examples/langchain-python-rag-privategpt/.gitignore old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/LICENSE b/examples/langchain-python-rag-privategpt/LICENSE old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/README.md b/examples/langchain-python-rag-privategpt/README.md old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/constants.py b/examples/langchain-python-rag-privategpt/constants.py old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/ingest.py b/examples/langchain-python-rag-privategpt/ingest.py old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/poetry.lock b/examples/langchain-python-rag-privategpt/poetry.lock old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/privateGPT.py b/examples/langchain-python-rag-privategpt/privateGPT.py old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/pyproject.toml b/examples/langchain-python-rag-privategpt/pyproject.toml old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-privategpt/requirements.txt b/examples/langchain-python-rag-privategpt/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-websummary/README.md b/examples/langchain-python-rag-websummary/README.md old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-websummary/main.py b/examples/langchain-python-rag-websummary/main.py old mode 100755 new mode 100644 diff --git a/examples/langchain-python-rag-websummary/requirements.txt b/examples/langchain-python-rag-websummary/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/langchain-python-simple/README.md b/examples/langchain-python-simple/README.md old mode 100755 new mode 100644 diff --git a/examples/langchain-python-simple/main.py b/examples/langchain-python-simple/main.py old mode 100755 new mode 100644 diff --git a/examples/langchain-python-simple/requirements.txt b/examples/langchain-python-simple/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/langchain-typescript-simple/README.md b/examples/langchain-typescript-simple/README.md old mode 100755 new mode 100644 diff --git a/examples/langchain-typescript-simple/main.ts b/examples/langchain-typescript-simple/main.ts old mode 100755 new mode 100644 diff --git a/examples/langchain-typescript-simple/package-lock.json b/examples/langchain-typescript-simple/package-lock.json old mode 100755 new mode 100644 diff --git a/examples/langchain-typescript-simple/package.json b/examples/langchain-typescript-simple/package.json old mode 100755 new mode 100644 diff --git a/examples/modelfile-mario/Modelfile b/examples/modelfile-mario/Modelfile old mode 100755 new mode 100644 diff --git a/examples/modelfile-mario/logo.png b/examples/modelfile-mario/logo.png old mode 100755 new mode 100644 diff --git a/examples/modelfile-mario/readme.md b/examples/modelfile-mario/readme.md old mode 100755 new mode 100644 diff --git a/examples/python-dockerit/Modelfile b/examples/python-dockerit/Modelfile old mode 100755 new mode 100644 diff --git a/examples/python-dockerit/README.md b/examples/python-dockerit/README.md old mode 100755 new mode 100644 diff --git a/examples/python-dockerit/dockerit.py b/examples/python-dockerit/dockerit.py old mode 100755 new mode 100644 diff --git a/examples/python-dockerit/requirements.txt b/examples/python-dockerit/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/python-json-datagenerator/predefinedschema.py b/examples/python-json-datagenerator/predefinedschema.py old mode 100755 new mode 100644 diff --git a/examples/python-json-datagenerator/randomaddresses.py b/examples/python-json-datagenerator/randomaddresses.py old mode 100755 new mode 100644 diff --git a/examples/python-json-datagenerator/readme.md b/examples/python-json-datagenerator/readme.md old mode 100755 new mode 100644 diff --git a/examples/python-json-datagenerator/requirements.txt b/examples/python-json-datagenerator/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/python-loganalysis/Modelfile b/examples/python-loganalysis/Modelfile old mode 100755 new mode 100644 diff --git a/examples/python-loganalysis/loganalysis.py b/examples/python-loganalysis/loganalysis.py old mode 100755 new mode 100644 diff --git a/examples/python-loganalysis/logtest.logfile b/examples/python-loganalysis/logtest.logfile old mode 100755 new mode 100644 diff --git a/examples/python-loganalysis/readme.md b/examples/python-loganalysis/readme.md old mode 100755 new mode 100644 diff --git a/examples/python-loganalysis/requirements.txt b/examples/python-loganalysis/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/python-rag-newssummary/README.md b/examples/python-rag-newssummary/README.md old mode 100755 new mode 100644 diff --git a/examples/python-rag-newssummary/requirements.txt b/examples/python-rag-newssummary/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/python-rag-newssummary/summ.py b/examples/python-rag-newssummary/summ.py old mode 100755 new mode 100644 diff --git a/examples/python-rag-newssummary/utils.py b/examples/python-rag-newssummary/utils.py old mode 100755 new mode 100644 diff --git a/examples/python-simplechat/client.py b/examples/python-simplechat/client.py old mode 100755 new mode 100644 diff --git a/examples/python-simplechat/readme.md b/examples/python-simplechat/readme.md old mode 100755 new mode 100644 diff --git a/examples/python-simplechat/requirements.txt b/examples/python-simplechat/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/python-simplegenerate/README.md b/examples/python-simplegenerate/README.md old mode 100755 new mode 100644 diff --git a/examples/python-simplegenerate/client.py b/examples/python-simplegenerate/client.py old mode 100755 new mode 100644 diff --git a/examples/python-simplegenerate/requirements.txt b/examples/python-simplegenerate/requirements.txt old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/extractemail.ts b/examples/typescript-functioncalling/extractemail.ts old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/extractwp.ts b/examples/typescript-functioncalling/extractwp.ts old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/info.txt b/examples/typescript-functioncalling/info.txt old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/package-lock.json b/examples/typescript-functioncalling/package-lock.json old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/package.json b/examples/typescript-functioncalling/package.json old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/readme.md b/examples/typescript-functioncalling/readme.md old mode 100755 new mode 100644 diff --git a/examples/typescript-functioncalling/wp.txt b/examples/typescript-functioncalling/wp.txt old mode 100755 new mode 100644 diff --git a/examples/typescript-mentors/.gitignore b/examples/typescript-mentors/.gitignore old mode 100755 new mode 100644 diff --git a/examples/typescript-mentors/README.md b/examples/typescript-mentors/README.md old mode 100755 new mode 100644 diff --git a/examples/typescript-mentors/character-generator.ts b/examples/typescript-mentors/character-generator.ts old mode 100755 new mode 100644 diff --git a/examples/typescript-mentors/mentors.ts b/examples/typescript-mentors/mentors.ts old mode 100755 new mode 100644 diff --git a/examples/typescript-mentors/package.json b/examples/typescript-mentors/package.json old mode 100755 new mode 100644 diff --git a/examples/typescript-simplechat/client.ts b/examples/typescript-simplechat/client.ts old mode 100755 new mode 100644 diff --git a/examples/typescript-simplechat/package.json b/examples/typescript-simplechat/package.json old mode 100755 new mode 100644 diff --git a/examples/typescript-simplechat/readme.md b/examples/typescript-simplechat/readme.md old mode 100755 new mode 100644 diff --git a/format/bytes.go b/format/bytes.go old mode 100755 new mode 100644 diff --git a/format/format.go b/format/format.go old mode 100755 new mode 100644 diff --git a/format/format_test.go b/format/format_test.go old mode 100755 new mode 100644 diff --git a/format/time.go b/format/time.go old mode 100755 new mode 100644 diff --git a/format/time_test.go b/format/time_test.go old mode 100755 new mode 100644 diff --git a/go.mod b/go.mod old mode 100755 new mode 100644 diff --git a/go.sum b/go.sum old mode 100755 new mode 100644 diff --git a/gpu/amd_common.go b/gpu/amd_common.go old mode 100755 new mode 100644 diff --git a/gpu/amd_hip_windows.go b/gpu/amd_hip_windows.go old mode 100755 new mode 100644 diff --git a/gpu/amd_linux.go b/gpu/amd_linux.go old mode 100755 new mode 100644 diff --git a/gpu/amd_windows.go b/gpu/amd_windows.go old mode 100755 new mode 100644 diff --git a/gpu/assets.go b/gpu/assets.go old mode 100755 new mode 100644 diff --git a/gpu/cpu_common.go b/gpu/cpu_common.go old mode 100755 new mode 100644 diff --git a/gpu/cuda_common.go b/gpu/cuda_common.go old mode 100755 new mode 100644 diff --git a/gpu/gpu.go b/gpu/gpu.go old mode 100755 new mode 100644 diff --git a/gpu/gpu_darwin.go b/gpu/gpu_darwin.go old mode 100755 new mode 100644 diff --git a/gpu/gpu_info.h b/gpu/gpu_info.h old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_cudart.c b/gpu/gpu_info_cudart.c old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_cudart.h b/gpu/gpu_info_cudart.h old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_darwin.h b/gpu/gpu_info_darwin.h old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_darwin.m b/gpu/gpu_info_darwin.m old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_nvcuda.c b/gpu/gpu_info_nvcuda.c old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_nvcuda.h b/gpu/gpu_info_nvcuda.h old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_nvml.c b/gpu/gpu_info_nvml.c old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_nvml.h b/gpu/gpu_info_nvml.h old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_oneapi.c b/gpu/gpu_info_oneapi.c old mode 100755 new mode 100644 diff --git a/gpu/gpu_info_oneapi.h b/gpu/gpu_info_oneapi.h old mode 100755 new mode 100644 diff --git a/gpu/gpu_linux.go b/gpu/gpu_linux.go old mode 100755 new mode 100644 diff --git a/gpu/gpu_oneapi.go b/gpu/gpu_oneapi.go old mode 100755 new mode 100644 diff --git a/gpu/gpu_test.go b/gpu/gpu_test.go old mode 100755 new mode 100644 diff --git a/gpu/gpu_windows.go b/gpu/gpu_windows.go old mode 100755 new mode 100644 diff --git a/gpu/types.go b/gpu/types.go old mode 100755 new mode 100644 diff --git a/integration/README.md b/integration/README.md old mode 100755 new mode 100644 diff --git a/integration/basic_test.go b/integration/basic_test.go old mode 100755 new mode 100644 diff --git a/integration/concurrency_test.go b/integration/concurrency_test.go old mode 100755 new mode 100644 diff --git a/integration/context_test.go b/integration/context_test.go old mode 100755 new mode 100644 diff --git a/integration/embed_test.go b/integration/embed_test.go old mode 100755 new mode 100644 diff --git a/integration/llm_image_test.go b/integration/llm_image_test.go old mode 100755 new mode 100644 diff --git a/integration/llm_test.go b/integration/llm_test.go old mode 100755 new mode 100644 diff --git a/integration/max_queue_test.go b/integration/max_queue_test.go old mode 100755 new mode 100644 diff --git a/integration/utils_test.go b/integration/utils_test.go old mode 100755 new mode 100644 diff --git a/llm/ext_server/CMakeLists.txt b/llm/ext_server/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/ext_server/httplib.h b/llm/ext_server/httplib.h old mode 100755 new mode 100644 diff --git a/llm/ext_server/json.hpp b/llm/ext_server/json.hpp old mode 100755 new mode 100644 diff --git a/llm/ext_server/server.cpp b/llm/ext_server/server.cpp old mode 100755 new mode 100644 diff --git a/llm/ext_server/utils.hpp b/llm/ext_server/utils.hpp old mode 100755 new mode 100644 diff --git a/llm/filetype.go b/llm/filetype.go old mode 100755 new mode 100644 diff --git a/llm/generate/gen_common.sh b/llm/generate/gen_common.sh old mode 100755 new mode 100644 diff --git a/llm/generate/gen_darwin.sh b/llm/generate/gen_darwin.sh old mode 100755 new mode 100644 diff --git a/llm/generate/gen_linux.sh b/llm/generate/gen_linux.sh old mode 100755 new mode 100644 diff --git a/llm/generate/gen_windows.ps1 b/llm/generate/gen_windows.ps1 old mode 100755 new mode 100644 diff --git a/llm/generate/generate_darwin.go b/llm/generate/generate_darwin.go old mode 100755 new mode 100644 diff --git a/llm/generate/generate_linux.go b/llm/generate/generate_linux.go old mode 100755 new mode 100644 diff --git a/llm/generate/generate_windows.go b/llm/generate/generate_windows.go old mode 100755 new mode 100644 diff --git a/llm/ggla.go b/llm/ggla.go old mode 100755 new mode 100644 diff --git a/llm/ggml.go b/llm/ggml.go old mode 100755 new mode 100644 diff --git a/llm/ggml_test.go b/llm/ggml_test.go old mode 100755 new mode 100644 diff --git a/llm/gguf.go b/llm/gguf.go old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.clang-tidy b/llm/llama.cpp/.clang-tidy old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/cloud-v-pipeline b/llm/llama.cpp/.devops/cloud-v-pipeline old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/full-cuda.Dockerfile b/llm/llama.cpp/.devops/full-cuda.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/full-rocm.Dockerfile b/llm/llama.cpp/.devops/full-rocm.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/full.Dockerfile b/llm/llama.cpp/.devops/full.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cli-cuda.Dockerfile b/llm/llama.cpp/.devops/llama-cli-cuda.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cli-intel.Dockerfile b/llm/llama.cpp/.devops/llama-cli-intel.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cli-rocm.Dockerfile b/llm/llama.cpp/.devops/llama-cli-rocm.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cli-vulkan.Dockerfile b/llm/llama.cpp/.devops/llama-cli-vulkan.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cli.Dockerfile b/llm/llama.cpp/.devops/llama-cli.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cpp-cuda.srpm.spec b/llm/llama.cpp/.devops/llama-cpp-cuda.srpm.spec old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-cpp.srpm.spec b/llm/llama.cpp/.devops/llama-cpp.srpm.spec old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-server-cuda.Dockerfile b/llm/llama.cpp/.devops/llama-server-cuda.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-server-intel.Dockerfile b/llm/llama.cpp/.devops/llama-server-intel.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-server-rocm.Dockerfile b/llm/llama.cpp/.devops/llama-server-rocm.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-server-vulkan.Dockerfile b/llm/llama.cpp/.devops/llama-server-vulkan.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/llama-server.Dockerfile b/llm/llama.cpp/.devops/llama-server.Dockerfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/apps.nix b/llm/llama.cpp/.devops/nix/apps.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/devshells.nix b/llm/llama.cpp/.devops/nix/devshells.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/docker.nix b/llm/llama.cpp/.devops/nix/docker.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/jetson-support.nix b/llm/llama.cpp/.devops/nix/jetson-support.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/nixpkgs-instances.nix b/llm/llama.cpp/.devops/nix/nixpkgs-instances.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/package.nix b/llm/llama.cpp/.devops/nix/package.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/scope.nix b/llm/llama.cpp/.devops/nix/scope.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/nix/sif.nix b/llm/llama.cpp/.devops/nix/sif.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.devops/tools.sh b/llm/llama.cpp/.devops/tools.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.dockerignore b/llm/llama.cpp/.dockerignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.ecrc b/llm/llama.cpp/.ecrc old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.editorconfig b/llm/llama.cpp/.editorconfig old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.flake8 b/llm/llama.cpp/.flake8 old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/01-bug-low.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/01-bug-low.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/02-bug-medium.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/02-bug-medium.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/03-bug-high.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/03-bug-high.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/04-bug-critical.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/04-bug-critical.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/05-enhancement.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/05-enhancement.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/06-research.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/06-research.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/07-refactor.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/07-refactor.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/ISSUE_TEMPLATE/config.yml b/llm/llama.cpp/.github/ISSUE_TEMPLATE/config.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/labeler.yml b/llm/llama.cpp/.github/labeler.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/pull_request_template.md b/llm/llama.cpp/.github/pull_request_template.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/bench.yml b/llm/llama.cpp/.github/workflows/bench.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/build.yml b/llm/llama.cpp/.github/workflows/build.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/close-issue.yml b/llm/llama.cpp/.github/workflows/close-issue.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/docker.yml b/llm/llama.cpp/.github/workflows/docker.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/editorconfig.yml b/llm/llama.cpp/.github/workflows/editorconfig.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/gguf-publish.yml b/llm/llama.cpp/.github/workflows/gguf-publish.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/labeler.yml b/llm/llama.cpp/.github/workflows/labeler.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/nix-ci-aarch64.yml b/llm/llama.cpp/.github/workflows/nix-ci-aarch64.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/nix-ci.yml b/llm/llama.cpp/.github/workflows/nix-ci.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/nix-flake-update.yml b/llm/llama.cpp/.github/workflows/nix-flake-update.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/nix-publish-flake.yml b/llm/llama.cpp/.github/workflows/nix-publish-flake.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/python-check-requirements.yml b/llm/llama.cpp/.github/workflows/python-check-requirements.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/python-lint.yml b/llm/llama.cpp/.github/workflows/python-lint.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/python-type-check.yml b/llm/llama.cpp/.github/workflows/python-type-check.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.github/workflows/server.yml b/llm/llama.cpp/.github/workflows/server.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.gitignore b/llm/llama.cpp/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.gitmodules b/llm/llama.cpp/.gitmodules old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/.pre-commit-config.yaml b/llm/llama.cpp/.pre-commit-config.yaml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/AUTHORS b/llm/llama.cpp/AUTHORS old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/CMakeLists.txt b/llm/llama.cpp/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/CMakePresets.json b/llm/llama.cpp/CMakePresets.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/CONTRIBUTING.md b/llm/llama.cpp/CONTRIBUTING.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/LICENSE b/llm/llama.cpp/LICENSE old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/Makefile b/llm/llama.cpp/Makefile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/Package.swift b/llm/llama.cpp/Package.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/README.md b/llm/llama.cpp/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/SECURITY.md b/llm/llama.cpp/SECURITY.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ci/README.md b/llm/llama.cpp/ci/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ci/run.sh b/llm/llama.cpp/ci/run.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/cmake/arm64-windows-llvm.cmake b/llm/llama.cpp/cmake/arm64-windows-llvm.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/cmake/arm64-windows-msvc.cmake b/llm/llama.cpp/cmake/arm64-windows-msvc.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/cmake/build-info.cmake b/llm/llama.cpp/cmake/build-info.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/cmake/git-vars.cmake b/llm/llama.cpp/cmake/git-vars.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/cmake/llama-config.cmake.in b/llm/llama.cpp/cmake/llama-config.cmake.in old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/cmake/llama.pc.in b/llm/llama.cpp/cmake/llama.pc.in old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/CMakeLists.txt b/llm/llama.cpp/common/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/base64.hpp b/llm/llama.cpp/common/base64.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/build-info.cpp.in b/llm/llama.cpp/common/build-info.cpp.in old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/cmake/build-info-gen-cpp.cmake b/llm/llama.cpp/common/cmake/build-info-gen-cpp.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/common.cpp b/llm/llama.cpp/common/common.cpp old mode 100755 new mode 100644 index 2e8374d50cafad99cb9f59eccb4ac5c22ed6b32b..56cad1af975f066fcb77af652a04e896eb3361a9 --- a/llm/llama.cpp/common/common.cpp +++ b/llm/llama.cpp/common/common.cpp @@ -2110,9 +2110,21 @@ struct llama_init_result llama_init_from_gpt_params(gpt_params & params) { loaded_la.adapter = llama_lora_adapter_init(model, la.path.c_str()); if (loaded_la.adapter == nullptr) { fprintf(stderr, "%s: error: failed to apply lora adapter '%s'\n", __func__, la.path.c_str()); - llama_free(lctx); - llama_free_model(model); - return iparams; + + // if that fails, try loading as ggla for compatibility + int err = llama_model_apply_lora_from_file(model, + la.path.c_str(), + la.scale, + nullptr, + params.n_threads); + if (err != 0) { + fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__); + llama_free(lctx); + llama_free_model(model); + return iparams; + } else { + break; + } } iparams.lora_adapters.push_back(loaded_la); // copy to list of loaded adapters } @@ -2178,6 +2190,8 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params & mparams.use_mmap = params.use_mmap; mparams.use_mlock = params.use_mlock; mparams.check_tensors = params.check_tensors; + mparams.progress_callback = params.progress_callback; + mparams.progress_callback_user_data = params.progress_callback_user_data; if (params.kv_overrides.empty()) { mparams.kv_overrides = NULL; } else { diff --git a/llm/llama.cpp/common/common.h b/llm/llama.cpp/common/common.h old mode 100755 new mode 100644 index d88966ece20aa73da262d047e6c0137e7a0e972f..c238cd7417ddd28b965af154ee86a9d88ec0294b --- a/llm/llama.cpp/common/common.h +++ b/llm/llama.cpp/common/common.h @@ -194,6 +194,13 @@ struct gpt_params { std::string mmproj = ""; // path to multimodal projector std::vector image; // path to image file(s) + // Called with a progress value between 0.0 and 1.0. Pass NULL to disable. + // If the provided progress_callback returns true, model loading continues. + // If it returns false, model loading is immediately aborted. + llama_progress_callback progress_callback = NULL; + // context pointer passed to the progress callback + void * progress_callback_user_data; + // embedding bool embedding = false; // get only sentence embedding int32_t embd_normalize = 2; // normalisation for embendings (-1=none, 0=max absolute int16, 1=taxicab, 2=euclidean, >2=p-norm) diff --git a/llm/llama.cpp/common/console.cpp b/llm/llama.cpp/common/console.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/console.h b/llm/llama.cpp/common/console.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/grammar-parser.cpp b/llm/llama.cpp/common/grammar-parser.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/grammar-parser.h b/llm/llama.cpp/common/grammar-parser.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/json-schema-to-grammar.cpp b/llm/llama.cpp/common/json-schema-to-grammar.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/json-schema-to-grammar.h b/llm/llama.cpp/common/json-schema-to-grammar.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/json.hpp b/llm/llama.cpp/common/json.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/log.h b/llm/llama.cpp/common/log.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/ngram-cache.cpp b/llm/llama.cpp/common/ngram-cache.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/ngram-cache.h b/llm/llama.cpp/common/ngram-cache.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/sampling.cpp b/llm/llama.cpp/common/sampling.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/sampling.h b/llm/llama.cpp/common/sampling.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/stb_image.h b/llm/llama.cpp/common/stb_image.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/train.cpp b/llm/llama.cpp/common/train.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/common/train.h b/llm/llama.cpp/common/train.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/convert_hf_to_gguf.py b/llm/llama.cpp/convert_hf_to_gguf.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/convert_hf_to_gguf_update.py b/llm/llama.cpp/convert_hf_to_gguf_update.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/convert_llama_ggml_to_gguf.py b/llm/llama.cpp/convert_llama_ggml_to_gguf.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/convert_lora_to_gguf.py b/llm/llama.cpp/convert_lora_to_gguf.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/android.md b/llm/llama.cpp/docs/android.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/backend/BLIS.md b/llm/llama.cpp/docs/backend/BLIS.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/backend/SYCL.md b/llm/llama.cpp/docs/backend/SYCL.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/build.md b/llm/llama.cpp/docs/build.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/development/HOWTO-add-model.md b/llm/llama.cpp/docs/development/HOWTO-add-model.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/development/debugging-tests.md b/llm/llama.cpp/docs/development/debugging-tests.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/development/llama-star/idea-arch.key b/llm/llama.cpp/docs/development/llama-star/idea-arch.key old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/development/llama-star/idea-arch.pdf b/llm/llama.cpp/docs/development/llama-star/idea-arch.pdf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/development/token_generation_performance_tips.md b/llm/llama.cpp/docs/development/token_generation_performance_tips.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/docker.md b/llm/llama.cpp/docs/docker.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/docs/install.md b/llm/llama.cpp/docs/install.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/CMakeLists.txt b/llm/llama.cpp/examples/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/Miku.sh b/llm/llama.cpp/examples/Miku.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/baby-llama/CMakeLists.txt b/llm/llama.cpp/examples/baby-llama/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/baby-llama/baby-llama.cpp b/llm/llama.cpp/examples/baby-llama/baby-llama.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/base-translate.sh b/llm/llama.cpp/examples/base-translate.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched-bench/CMakeLists.txt b/llm/llama.cpp/examples/batched-bench/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched-bench/README.md b/llm/llama.cpp/examples/batched-bench/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched-bench/batched-bench.cpp b/llm/llama.cpp/examples/batched-bench/batched-bench.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched.swift/.gitignore b/llm/llama.cpp/examples/batched.swift/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched.swift/Makefile b/llm/llama.cpp/examples/batched.swift/Makefile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched.swift/Package.swift b/llm/llama.cpp/examples/batched.swift/Package.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched.swift/README.md b/llm/llama.cpp/examples/batched.swift/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched.swift/Sources/main.swift b/llm/llama.cpp/examples/batched.swift/Sources/main.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched/CMakeLists.txt b/llm/llama.cpp/examples/batched/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched/README.md b/llm/llama.cpp/examples/batched/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/batched/batched.cpp b/llm/llama.cpp/examples/batched/batched.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/benchmark/CMakeLists.txt b/llm/llama.cpp/examples/benchmark/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/benchmark/benchmark-matmult.cpp b/llm/llama.cpp/examples/benchmark/benchmark-matmult.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/chat-13B.sh b/llm/llama.cpp/examples/chat-13B.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/chat-persistent.sh b/llm/llama.cpp/examples/chat-persistent.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/chat-vicuna.sh b/llm/llama.cpp/examples/chat-vicuna.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/chat.sh b/llm/llama.cpp/examples/chat.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/convert-llama2c-to-ggml/CMakeLists.txt b/llm/llama.cpp/examples/convert-llama2c-to-ggml/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/convert-llama2c-to-ggml/README.md b/llm/llama.cpp/examples/convert-llama2c-to-ggml/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp b/llm/llama.cpp/examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/convert_legacy_llama.py b/llm/llama.cpp/examples/convert_legacy_llama.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/CMakeLists.txt b/llm/llama.cpp/examples/cvector-generator/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/README.md b/llm/llama.cpp/examples/cvector-generator/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/completions.txt b/llm/llama.cpp/examples/cvector-generator/completions.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/cvector-generator.cpp b/llm/llama.cpp/examples/cvector-generator/cvector-generator.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/mean.hpp b/llm/llama.cpp/examples/cvector-generator/mean.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/negative.txt b/llm/llama.cpp/examples/cvector-generator/negative.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/pca.hpp b/llm/llama.cpp/examples/cvector-generator/pca.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/cvector-generator/positive.txt b/llm/llama.cpp/examples/cvector-generator/positive.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/deprecation-warning/README.md b/llm/llama.cpp/examples/deprecation-warning/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/deprecation-warning/deprecation-warning.cpp b/llm/llama.cpp/examples/deprecation-warning/deprecation-warning.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/embedding/CMakeLists.txt b/llm/llama.cpp/examples/embedding/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/embedding/README.md b/llm/llama.cpp/examples/embedding/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/embedding/embedding.cpp b/llm/llama.cpp/examples/embedding/embedding.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/eval-callback/CMakeLists.txt b/llm/llama.cpp/examples/eval-callback/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/eval-callback/README.md b/llm/llama.cpp/examples/eval-callback/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/eval-callback/eval-callback.cpp b/llm/llama.cpp/examples/eval-callback/eval-callback.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/export-lora/CMakeLists.txt b/llm/llama.cpp/examples/export-lora/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/export-lora/README.md b/llm/llama.cpp/examples/export-lora/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/export-lora/export-lora.cpp b/llm/llama.cpp/examples/export-lora/export-lora.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gbnf-validator/CMakeLists.txt b/llm/llama.cpp/examples/gbnf-validator/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gbnf-validator/gbnf-validator.cpp b/llm/llama.cpp/examples/gbnf-validator/gbnf-validator.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/CMakeLists.txt b/llm/llama.cpp/examples/gguf-hash/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/README.md b/llm/llama.cpp/examples/gguf-hash/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/rotate-bits/package.json b/llm/llama.cpp/examples/gguf-hash/deps/rotate-bits/package.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/rotate-bits/rotate-bits.h b/llm/llama.cpp/examples/gguf-hash/deps/rotate-bits/rotate-bits.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/sha1/package.json b/llm/llama.cpp/examples/gguf-hash/deps/sha1/package.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/sha1/sha1.c b/llm/llama.cpp/examples/gguf-hash/deps/sha1/sha1.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/sha1/sha1.h b/llm/llama.cpp/examples/gguf-hash/deps/sha1/sha1.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/sha256/package.json b/llm/llama.cpp/examples/gguf-hash/deps/sha256/package.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/sha256/sha256.c b/llm/llama.cpp/examples/gguf-hash/deps/sha256/sha256.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/sha256/sha256.h b/llm/llama.cpp/examples/gguf-hash/deps/sha256/sha256.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/xxhash/clib.json b/llm/llama.cpp/examples/gguf-hash/deps/xxhash/clib.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/xxhash/xxhash.c b/llm/llama.cpp/examples/gguf-hash/deps/xxhash/xxhash.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/deps/xxhash/xxhash.h b/llm/llama.cpp/examples/gguf-hash/deps/xxhash/xxhash.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-hash/gguf-hash.cpp b/llm/llama.cpp/examples/gguf-hash/gguf-hash.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-split/CMakeLists.txt b/llm/llama.cpp/examples/gguf-split/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-split/README.md b/llm/llama.cpp/examples/gguf-split/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-split/gguf-split.cpp b/llm/llama.cpp/examples/gguf-split/gguf-split.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf-split/tests.sh b/llm/llama.cpp/examples/gguf-split/tests.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf/CMakeLists.txt b/llm/llama.cpp/examples/gguf/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gguf/gguf.cpp b/llm/llama.cpp/examples/gguf/gguf.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gritlm/CMakeLists.txt b/llm/llama.cpp/examples/gritlm/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gritlm/README.md b/llm/llama.cpp/examples/gritlm/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/gritlm/gritlm.cpp b/llm/llama.cpp/examples/gritlm/gritlm.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/imatrix/CMakeLists.txt b/llm/llama.cpp/examples/imatrix/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/imatrix/README.md b/llm/llama.cpp/examples/imatrix/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/imatrix/imatrix.cpp b/llm/llama.cpp/examples/imatrix/imatrix.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/infill/CMakeLists.txt b/llm/llama.cpp/examples/infill/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/infill/README.md b/llm/llama.cpp/examples/infill/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/infill/infill.cpp b/llm/llama.cpp/examples/infill/infill.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/jeopardy/README.md b/llm/llama.cpp/examples/jeopardy/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/jeopardy/graph.py b/llm/llama.cpp/examples/jeopardy/graph.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/jeopardy/jeopardy.sh b/llm/llama.cpp/examples/jeopardy/jeopardy.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/jeopardy/qasheet.csv b/llm/llama.cpp/examples/jeopardy/qasheet.csv old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/jeopardy/questions.txt b/llm/llama.cpp/examples/jeopardy/questions.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/json_schema_pydantic_example.py b/llm/llama.cpp/examples/json_schema_pydantic_example.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/json_schema_to_grammar.py b/llm/llama.cpp/examples/json_schema_to_grammar.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama-bench/CMakeLists.txt b/llm/llama.cpp/examples/llama-bench/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama-bench/README.md b/llm/llama.cpp/examples/llama-bench/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama-bench/llama-bench.cpp b/llm/llama.cpp/examples/llama-bench/llama-bench.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/.gitignore b/llm/llama.cpp/examples/llama.android/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/README.md b/llm/llama.cpp/examples/llama.android/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/.gitignore b/llm/llama.cpp/examples/llama.android/app/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/build.gradle.kts b/llm/llama.cpp/examples/llama.android/app/build.gradle.kts old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/proguard-rules.pro b/llm/llama.cpp/examples/llama.android/app/proguard-rules.pro old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/AndroidManifest.xml b/llm/llama.cpp/examples/llama.android/app/src/main/AndroidManifest.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/Downloadable.kt b/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/Downloadable.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/MainActivity.kt b/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/MainActivity.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/MainViewModel.kt b/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/MainViewModel.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/ui/theme/Color.kt b/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/ui/theme/Color.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/ui/theme/Theme.kt b/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/ui/theme/Theme.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/ui/theme/Type.kt b/llm/llama.cpp/examples/llama.android/app/src/main/java/com/example/llama/ui/theme/Type.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/drawable/ic_launcher_background.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/drawable/ic_launcher_background.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/drawable/ic_launcher_foreground.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/drawable/ic_launcher_foreground.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-anydpi/ic_launcher.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-anydpi/ic_launcher.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-anydpi/ic_launcher_round.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-anydpi/ic_launcher_round.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-hdpi/ic_launcher.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-hdpi/ic_launcher.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-hdpi/ic_launcher_round.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-hdpi/ic_launcher_round.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-mdpi/ic_launcher.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-mdpi/ic_launcher.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-mdpi/ic_launcher_round.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-mdpi/ic_launcher_round.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xhdpi/ic_launcher.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xhdpi/ic_launcher.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xhdpi/ic_launcher_round.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xhdpi/ic_launcher_round.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxhdpi/ic_launcher.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxhdpi/ic_launcher.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxhdpi/ic_launcher_round.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxhdpi/ic_launcher_round.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxxhdpi/ic_launcher.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxxhdpi/ic_launcher.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxxhdpi/ic_launcher_round.webp b/llm/llama.cpp/examples/llama.android/app/src/main/res/mipmap-xxxhdpi/ic_launcher_round.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/values/colors.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/values/colors.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/values/strings.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/values/strings.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/values/themes.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/values/themes.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/xml/backup_rules.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/xml/backup_rules.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/app/src/main/res/xml/data_extraction_rules.xml b/llm/llama.cpp/examples/llama.android/app/src/main/res/xml/data_extraction_rules.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/build.gradle.kts b/llm/llama.cpp/examples/llama.android/build.gradle.kts old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/gradle.properties b/llm/llama.cpp/examples/llama.android/gradle.properties old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/gradle/wrapper/gradle-wrapper.jar b/llm/llama.cpp/examples/llama.android/gradle/wrapper/gradle-wrapper.jar old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/gradle/wrapper/gradle-wrapper.properties b/llm/llama.cpp/examples/llama.android/gradle/wrapper/gradle-wrapper.properties old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/gradlew b/llm/llama.cpp/examples/llama.android/gradlew old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/.gitignore b/llm/llama.cpp/examples/llama.android/llama/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/build.gradle.kts b/llm/llama.cpp/examples/llama.android/llama/build.gradle.kts old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/consumer-rules.pro b/llm/llama.cpp/examples/llama.android/llama/consumer-rules.pro old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/proguard-rules.pro b/llm/llama.cpp/examples/llama.android/llama/proguard-rules.pro old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/src/androidTest/java/android/llama/cpp/ExampleInstrumentedTest.kt b/llm/llama.cpp/examples/llama.android/llama/src/androidTest/java/android/llama/cpp/ExampleInstrumentedTest.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/src/main/AndroidManifest.xml b/llm/llama.cpp/examples/llama.android/llama/src/main/AndroidManifest.xml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/src/main/cpp/CMakeLists.txt b/llm/llama.cpp/examples/llama.android/llama/src/main/cpp/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/src/main/cpp/llama-android.cpp b/llm/llama.cpp/examples/llama.android/llama/src/main/cpp/llama-android.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/src/main/java/android/llama/cpp/LLamaAndroid.kt b/llm/llama.cpp/examples/llama.android/llama/src/main/java/android/llama/cpp/LLamaAndroid.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/llama/src/test/java/android/llama/cpp/ExampleUnitTest.kt b/llm/llama.cpp/examples/llama.android/llama/src/test/java/android/llama/cpp/ExampleUnitTest.kt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.android/settings.gradle.kts b/llm/llama.cpp/examples/llama.android/settings.gradle.kts old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/.gitignore b/llm/llama.cpp/examples/llama.swiftui/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/README.md b/llm/llama.cpp/examples/llama.swiftui/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift b/llm/llama.cpp/examples/llama.swiftui/llama.cpp.swift/LibLlama.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui.xcodeproj/project.pbxproj b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui.xcodeproj/project.pbxproj old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui.xcodeproj/project.xcworkspace/contents.xcworkspacedata b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui.xcodeproj/project.xcworkspace/contents.xcworkspacedata old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Assets.xcassets/AppIcon.appiconset/Contents.json b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Assets.xcassets/AppIcon.appiconset/Contents.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Assets.xcassets/Contents.json b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Assets.xcassets/Contents.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Models/LlamaState.swift b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Models/LlamaState.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Resources/models/.gitignore b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/Resources/models/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/ContentView.swift b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/ContentView.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/DownloadButton.swift b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/DownloadButton.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/InputButton.swift b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/InputButton.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/LoadCustomButton.swift b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/UI/LoadCustomButton.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/llama_swiftuiApp.swift b/llm/llama.cpp/examples/llama.swiftui/llama.swiftui/llama_swiftuiApp.swift old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llama.vim b/llm/llama.cpp/examples/llama.vim old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/CMakeLists.txt b/llm/llama.cpp/examples/llava/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/MobileVLM-README.md b/llm/llama.cpp/examples/llava/MobileVLM-README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/README.md b/llm/llama.cpp/examples/llava/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/android/adb_run.sh b/llm/llama.cpp/examples/llava/android/adb_run.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/android/build_64.sh b/llm/llama.cpp/examples/llava/android/build_64.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/clip.cpp b/llm/llama.cpp/examples/llava/clip.cpp old mode 100755 new mode 100644 index 7cda5f10c4b05dce52334ec6636c0d0fa7bcc1b6..b86c7a58ea6f766418c1694669d62b5c7b3a1b52 --- a/llm/llama.cpp/examples/llava/clip.cpp +++ b/llm/llama.cpp/examples/llava/clip.cpp @@ -3,6 +3,7 @@ // I'll gradually clean and extend it // Note: Even when using identical normalized image inputs (see normalize_image_u8_to_f32()) we have a significant difference in resulting embeddings compared to pytorch #include "clip.h" +#include "common.h" #include "log.h" #include "ggml.h" #include "ggml-alloc.h" @@ -36,6 +37,14 @@ #include #include +#if defined(_WIN32) +#define WIN32_LEAN_AND_MEAN +#ifndef NOMINMAX + #define NOMINMAX +#endif +#include +#endif + //#define CLIP_DEBUG_FUNCTIONS // RGB uint8 image @@ -1064,7 +1073,22 @@ struct clip_ctx * clip_model_load(const char * fname, const int verbosity = 1) { return nullptr; } +#ifdef _WIN32 + int wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, NULL, 0); + if (!wlen) { + return NULL; + } + wchar_t * wbuf = (wchar_t *) malloc(wlen * sizeof(wchar_t)); + wlen = MultiByteToWideChar(CP_UTF8, 0, fname, -1, wbuf, wlen); + if (!wlen) { + free(wbuf); + return NULL; + } + auto fin = std::ifstream(wbuf, std::ios::binary); + free(wbuf); +#else auto fin = std::ifstream(fname, std::ios::binary); +#endif if (!fin) { LOG_TEE("cannot open model file for loading tensors\n"); clip_free(new_clip); diff --git a/llm/llama.cpp/examples/llava/clip.h b/llm/llama.cpp/examples/llava/clip.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/convert_image_encoder_to_gguf.py b/llm/llama.cpp/examples/llava/convert_image_encoder_to_gguf.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/llava-cli.cpp b/llm/llama.cpp/examples/llava/llava-cli.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/llava.cpp b/llm/llama.cpp/examples/llava/llava.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/llava.h b/llm/llama.cpp/examples/llava/llava.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/llava_surgery.py b/llm/llama.cpp/examples/llava/llava_surgery.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/llava_surgery_v2.py b/llm/llama.cpp/examples/llava/llava_surgery_v2.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llava/requirements.txt b/llm/llama.cpp/examples/llava/requirements.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/llm.vim b/llm/llama.cpp/examples/llm.vim old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookahead/CMakeLists.txt b/llm/llama.cpp/examples/lookahead/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookahead/README.md b/llm/llama.cpp/examples/lookahead/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookahead/lookahead.cpp b/llm/llama.cpp/examples/lookahead/lookahead.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookup/CMakeLists.txt b/llm/llama.cpp/examples/lookup/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookup/README.md b/llm/llama.cpp/examples/lookup/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookup/lookup-create.cpp b/llm/llama.cpp/examples/lookup/lookup-create.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookup/lookup-merge.cpp b/llm/llama.cpp/examples/lookup/lookup-merge.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookup/lookup-stats.cpp b/llm/llama.cpp/examples/lookup/lookup-stats.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/lookup/lookup.cpp b/llm/llama.cpp/examples/lookup/lookup.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/main-cmake-pkg/.gitignore b/llm/llama.cpp/examples/main-cmake-pkg/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/main-cmake-pkg/CMakeLists.txt b/llm/llama.cpp/examples/main-cmake-pkg/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/main-cmake-pkg/README.md b/llm/llama.cpp/examples/main-cmake-pkg/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/main/CMakeLists.txt b/llm/llama.cpp/examples/main/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/main/README.md b/llm/llama.cpp/examples/main/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/main/main.cpp b/llm/llama.cpp/examples/main/main.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/parallel/CMakeLists.txt b/llm/llama.cpp/examples/parallel/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/parallel/README.md b/llm/llama.cpp/examples/parallel/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/parallel/parallel.cpp b/llm/llama.cpp/examples/parallel/parallel.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/passkey/CMakeLists.txt b/llm/llama.cpp/examples/passkey/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/passkey/README.md b/llm/llama.cpp/examples/passkey/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/passkey/passkey.cpp b/llm/llama.cpp/examples/passkey/passkey.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/perplexity/CMakeLists.txt b/llm/llama.cpp/examples/perplexity/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/perplexity/README.md b/llm/llama.cpp/examples/perplexity/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/perplexity/perplexity.cpp b/llm/llama.cpp/examples/perplexity/perplexity.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/pydantic_models_to_grammar.py b/llm/llama.cpp/examples/pydantic_models_to_grammar.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/pydantic_models_to_grammar_examples.py b/llm/llama.cpp/examples/pydantic_models_to_grammar_examples.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/quantize-stats/CMakeLists.txt b/llm/llama.cpp/examples/quantize-stats/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/quantize-stats/quantize-stats.cpp b/llm/llama.cpp/examples/quantize-stats/quantize-stats.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/quantize/CMakeLists.txt b/llm/llama.cpp/examples/quantize/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/quantize/README.md b/llm/llama.cpp/examples/quantize/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/quantize/quantize.cpp b/llm/llama.cpp/examples/quantize/quantize.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/quantize/tests.sh b/llm/llama.cpp/examples/quantize/tests.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/reason-act.sh b/llm/llama.cpp/examples/reason-act.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/regex_to_grammar.py b/llm/llama.cpp/examples/regex_to_grammar.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/retrieval/CMakeLists.txt b/llm/llama.cpp/examples/retrieval/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/retrieval/README.md b/llm/llama.cpp/examples/retrieval/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/retrieval/retrieval.cpp b/llm/llama.cpp/examples/retrieval/retrieval.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/rpc/CMakeLists.txt b/llm/llama.cpp/examples/rpc/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/rpc/README.md b/llm/llama.cpp/examples/rpc/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/rpc/rpc-server.cpp b/llm/llama.cpp/examples/rpc/rpc-server.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/save-load-state/CMakeLists.txt b/llm/llama.cpp/examples/save-load-state/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/save-load-state/save-load-state.cpp b/llm/llama.cpp/examples/save-load-state/save-load-state.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server-llama2-13B.sh b/llm/llama.cpp/examples/server-llama2-13B.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/CMakeLists.txt b/llm/llama.cpp/examples/server/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/README.md b/llm/llama.cpp/examples/server/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/bench/README.md b/llm/llama.cpp/examples/server/bench/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/bench/bench.py b/llm/llama.cpp/examples/server/bench/bench.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/bench/prometheus.yml b/llm/llama.cpp/examples/server/bench/prometheus.yml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/bench/requirements.txt b/llm/llama.cpp/examples/server/bench/requirements.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/bench/script.js b/llm/llama.cpp/examples/server/bench/script.js old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/chat-llama2.sh b/llm/llama.cpp/examples/server/chat-llama2.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/chat.mjs b/llm/llama.cpp/examples/server/chat.mjs old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/chat.sh b/llm/llama.cpp/examples/server/chat.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/deps.sh b/llm/llama.cpp/examples/server/deps.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/httplib.h b/llm/llama.cpp/examples/server/httplib.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/colorthemes.css b/llm/llama.cpp/examples/server/public/colorthemes.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/completion.js b/llm/llama.cpp/examples/server/public/completion.js old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/favicon.ico b/llm/llama.cpp/examples/server/public/favicon.ico old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/index-new.html b/llm/llama.cpp/examples/server/public/index-new.html old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/index.html b/llm/llama.cpp/examples/server/public/index.html old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/index.js b/llm/llama.cpp/examples/server/public/index.js old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/json-schema-to-grammar.mjs b/llm/llama.cpp/examples/server/public/json-schema-to-grammar.mjs old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/prompt-formats.js b/llm/llama.cpp/examples/server/public/prompt-formats.js old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/style.css b/llm/llama.cpp/examples/server/public/style.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/system-prompts.js b/llm/llama.cpp/examples/server/public/system-prompts.js old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/theme-beeninorder.css b/llm/llama.cpp/examples/server/public/theme-beeninorder.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/theme-ketivah.css b/llm/llama.cpp/examples/server/public/theme-ketivah.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/theme-mangotango.css b/llm/llama.cpp/examples/server/public/theme-mangotango.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/theme-playground.css b/llm/llama.cpp/examples/server/public/theme-playground.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/theme-polarnight.css b/llm/llama.cpp/examples/server/public/theme-polarnight.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public/theme-snowstorm.css b/llm/llama.cpp/examples/server/public/theme-snowstorm.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/datautils.mjs b/llm/llama.cpp/examples/server/public_simplechat/datautils.mjs old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/index.html b/llm/llama.cpp/examples/server/public_simplechat/index.html old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/readme.md b/llm/llama.cpp/examples/server/public_simplechat/readme.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/simplechat.css b/llm/llama.cpp/examples/server/public_simplechat/simplechat.css old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/simplechat.js b/llm/llama.cpp/examples/server/public_simplechat/simplechat.js old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/simplechat_screens.webp b/llm/llama.cpp/examples/server/public_simplechat/simplechat_screens.webp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/public_simplechat/ui.mjs b/llm/llama.cpp/examples/server/public_simplechat/ui.mjs old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/server.cpp b/llm/llama.cpp/examples/server/server.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/README.md b/llm/llama.cpp/examples/server/tests/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/embeddings.feature b/llm/llama.cpp/examples/server/tests/features/embeddings.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/environment.py b/llm/llama.cpp/examples/server/tests/features/environment.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/issues.feature b/llm/llama.cpp/examples/server/tests/features/issues.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/lora.feature b/llm/llama.cpp/examples/server/tests/features/lora.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/parallel.feature b/llm/llama.cpp/examples/server/tests/features/parallel.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/passkey.feature b/llm/llama.cpp/examples/server/tests/features/passkey.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/results.feature b/llm/llama.cpp/examples/server/tests/features/results.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/security.feature b/llm/llama.cpp/examples/server/tests/features/security.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/server.feature b/llm/llama.cpp/examples/server/tests/features/server.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/slotsave.feature b/llm/llama.cpp/examples/server/tests/features/slotsave.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/steps/steps.py b/llm/llama.cpp/examples/server/tests/features/steps/steps.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/features/wrong_usages.feature b/llm/llama.cpp/examples/server/tests/features/wrong_usages.feature old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/requirements.txt b/llm/llama.cpp/examples/server/tests/requirements.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/tests/tests.sh b/llm/llama.cpp/examples/server/tests/tests.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/README.md b/llm/llama.cpp/examples/server/themes/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/buttons-top/README.md b/llm/llama.cpp/examples/server/themes/buttons-top/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/buttons-top/buttons_top.png b/llm/llama.cpp/examples/server/themes/buttons-top/buttons_top.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/buttons-top/favicon.ico b/llm/llama.cpp/examples/server/themes/buttons-top/favicon.ico old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/buttons-top/index.html b/llm/llama.cpp/examples/server/themes/buttons-top/index.html old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/wild/README.md b/llm/llama.cpp/examples/server/themes/wild/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/wild/favicon.ico b/llm/llama.cpp/examples/server/themes/wild/favicon.ico old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/wild/index.html b/llm/llama.cpp/examples/server/themes/wild/index.html old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/wild/llama_cpp.png b/llm/llama.cpp/examples/server/themes/wild/llama_cpp.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/wild/llamapattern.png b/llm/llama.cpp/examples/server/themes/wild/llamapattern.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/themes/wild/wild.png b/llm/llama.cpp/examples/server/themes/wild/wild.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server/utils.hpp b/llm/llama.cpp/examples/server/utils.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/server_embd.py b/llm/llama.cpp/examples/server_embd.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/simple/CMakeLists.txt b/llm/llama.cpp/examples/simple/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/simple/README.md b/llm/llama.cpp/examples/simple/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/simple/simple.cpp b/llm/llama.cpp/examples/simple/simple.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/speculative/CMakeLists.txt b/llm/llama.cpp/examples/speculative/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/speculative/README.md b/llm/llama.cpp/examples/speculative/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/speculative/speculative.cpp b/llm/llama.cpp/examples/speculative/speculative.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/sycl/CMakeLists.txt b/llm/llama.cpp/examples/sycl/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/sycl/README.md b/llm/llama.cpp/examples/sycl/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/sycl/build.sh b/llm/llama.cpp/examples/sycl/build.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/sycl/ls-sycl-device.cpp b/llm/llama.cpp/examples/sycl/ls-sycl-device.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/sycl/run-llama2.sh b/llm/llama.cpp/examples/sycl/run-llama2.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/tokenize/CMakeLists.txt b/llm/llama.cpp/examples/tokenize/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/tokenize/tokenize.cpp b/llm/llama.cpp/examples/tokenize/tokenize.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/examples/ts-type-to-grammar.sh b/llm/llama.cpp/examples/ts-type-to-grammar.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/flake.lock b/llm/llama.cpp/flake.lock old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/flake.nix b/llm/llama.cpp/flake.nix old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/.gitignore b/llm/llama.cpp/ggml/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/CMakeLists.txt b/llm/llama.cpp/ggml/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/cmake/FindSIMD.cmake b/llm/llama.cpp/ggml/cmake/FindSIMD.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-alloc.h b/llm/llama.cpp/ggml/include/ggml-alloc.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-backend.h b/llm/llama.cpp/ggml/include/ggml-backend.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-blas.h b/llm/llama.cpp/ggml/include/ggml-blas.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-cann.h b/llm/llama.cpp/ggml/include/ggml-cann.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-cuda.h b/llm/llama.cpp/ggml/include/ggml-cuda.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-kompute.h b/llm/llama.cpp/ggml/include/ggml-kompute.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-metal.h b/llm/llama.cpp/ggml/include/ggml-metal.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-rpc.h b/llm/llama.cpp/ggml/include/ggml-rpc.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-sycl.h b/llm/llama.cpp/ggml/include/ggml-sycl.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml-vulkan.h b/llm/llama.cpp/ggml/include/ggml-vulkan.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/include/ggml.h b/llm/llama.cpp/ggml/include/ggml.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/CMakeLists.txt b/llm/llama.cpp/ggml/src/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-aarch64.c b/llm/llama.cpp/ggml/src/ggml-aarch64.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-aarch64.h b/llm/llama.cpp/ggml/src/ggml-aarch64.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-alloc.c b/llm/llama.cpp/ggml/src/ggml-alloc.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-backend-impl.h b/llm/llama.cpp/ggml/src/ggml-backend-impl.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-backend.c b/llm/llama.cpp/ggml/src/ggml-backend.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-blas.cpp b/llm/llama.cpp/ggml/src/ggml-blas.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann.cpp b/llm/llama.cpp/ggml/src/ggml-cann.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/.clang-format b/llm/llama.cpp/ggml/src/ggml-cann/.clang-format old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/Doxyfile b/llm/llama.cpp/ggml/src/ggml-cann/Doxyfile old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/acl_tensor.cpp b/llm/llama.cpp/ggml/src/ggml-cann/acl_tensor.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/acl_tensor.h b/llm/llama.cpp/ggml/src/ggml-cann/acl_tensor.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/aclnn_ops.cpp b/llm/llama.cpp/ggml/src/ggml-cann/aclnn_ops.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/aclnn_ops.h b/llm/llama.cpp/ggml/src/ggml-cann/aclnn_ops.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/common.h b/llm/llama.cpp/ggml/src/ggml-cann/common.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/CMakeLists.txt b/llm/llama.cpp/ggml/src/ggml-cann/kernels/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/ascendc_kernels.h b/llm/llama.cpp/ggml/src/ggml-cann/kernels/ascendc_kernels.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/dup.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/dup.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_f16.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_f16.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_f32.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_f32.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_q4_0.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_q4_0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_q8_0.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/get_row_q8_0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/quantize_f16_q8_0.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/quantize_f16_q8_0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/quantize_f32_q8_0.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/quantize_f32_q8_0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cann/kernels/quantize_float_to_q4_0.cpp b/llm/llama.cpp/ggml/src/ggml-cann/kernels/quantize_float_to_q4_0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-common.h b/llm/llama.cpp/ggml/src/ggml-common.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda.cu b/llm/llama.cpp/ggml/src/ggml-cuda.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/acc.cu b/llm/llama.cpp/ggml/src/ggml-cuda/acc.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/acc.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/acc.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/arange.cu b/llm/llama.cpp/ggml/src/ggml-cuda/arange.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/arange.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/arange.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/argsort.cu b/llm/llama.cpp/ggml/src/ggml-cuda/argsort.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/argsort.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/argsort.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/binbcast.cu b/llm/llama.cpp/ggml/src/ggml-cuda/binbcast.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/binbcast.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/binbcast.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/clamp.cu b/llm/llama.cpp/ggml/src/ggml-cuda/clamp.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/clamp.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/clamp.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/concat.cu b/llm/llama.cpp/ggml/src/ggml-cuda/concat.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/concat.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/concat.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/conv-transpose-1d.cu b/llm/llama.cpp/ggml/src/ggml-cuda/conv-transpose-1d.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/conv-transpose-1d.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/conv-transpose-1d.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/convert.cu b/llm/llama.cpp/ggml/src/ggml-cuda/convert.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/convert.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/convert.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/cpy.cu b/llm/llama.cpp/ggml/src/ggml-cuda/cpy.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/cpy.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/cpy.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/dequantize.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/dequantize.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/diagmask.cu b/llm/llama.cpp/ggml/src/ggml-cuda/diagmask.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/diagmask.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/diagmask.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/dmmv.cu b/llm/llama.cpp/ggml/src/ggml-cuda/dmmv.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/dmmv.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/dmmv.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-common.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-common.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f16.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f16.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f32.cu b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f32.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f32.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-tile-f32.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-vec-f16.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-vec-f16.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-vec-f32.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-vec-f32.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn-wmma-f16.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn-wmma-f16.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn.cu b/llm/llama.cpp/ggml/src/ggml-cuda/fattn.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/fattn.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/fattn.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/getrows.cu b/llm/llama.cpp/ggml/src/ggml-cuda/getrows.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/getrows.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/getrows.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/im2col.cu b/llm/llama.cpp/ggml/src/ggml-cuda/im2col.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/im2col.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/im2col.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/mma.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/mma.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/mmq.cu b/llm/llama.cpp/ggml/src/ggml-cuda/mmq.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/mmq.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/mmq.cuh old mode 100755 new mode 100644 index 703c620c70f21636e67a434896346c0017258f97..2306db89f2f72884a54d16bf03bd96c4ceee25e7 --- a/llm/llama.cpp/ggml/src/ggml-cuda/mmq.cuh +++ b/llm/llama.cpp/ggml/src/ggml-cuda/mmq.cuh @@ -2580,7 +2580,7 @@ template __launch_bounds__(WARP_SIZE*nwarps, 2) #endif // __CUDA_ARCH__ >= CC_VOLTA #endif // defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__) -static __global__ __launch_bounds__(1024) void mul_mat_q( +static __global__ __launch_bounds__(256) void mul_mat_q( const char * __restrict__ x, const char * __restrict__ yc, float * __restrict__ dst, float * __restrict__ tmp_fixup, const int ne00, const int ne01, const int stride01, const int ne10, const int ne11, const int stride11, const int ne0) { diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/mmvq.cu b/llm/llama.cpp/ggml/src/ggml-cuda/mmvq.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/mmvq.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/mmvq.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/norm.cu b/llm/llama.cpp/ggml/src/ggml-cuda/norm.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/norm.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/norm.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/pad.cu b/llm/llama.cpp/ggml/src/ggml-cuda/pad.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/pad.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/pad.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/pool2d.cu b/llm/llama.cpp/ggml/src/ggml-cuda/pool2d.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/pool2d.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/pool2d.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/quantize.cu b/llm/llama.cpp/ggml/src/ggml-cuda/quantize.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/quantize.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/quantize.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/rope.cu b/llm/llama.cpp/ggml/src/ggml-cuda/rope.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/rope.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/rope.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/scale.cu b/llm/llama.cpp/ggml/src/ggml-cuda/scale.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/scale.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/scale.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/softmax.cu b/llm/llama.cpp/ggml/src/ggml-cuda/softmax.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/softmax.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/softmax.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/sumrows.cu b/llm/llama.cpp/ggml/src/ggml-cuda/sumrows.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/sumrows.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/sumrows.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-f16-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_0-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q4_1-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_0-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q5_1-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs128-q8_0-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs256-f16-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f16-instance-hs64-f16-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-f16-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_0-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q4_1-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_0-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q5_1-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs128-q8_0-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs256-f16-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-f16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-vec-f32-instance-hs64-f16-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqfloat-cpb32.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb16.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb32.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/fattn-wmma-f16-instance-kqhalf-cpb8.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/generate_cu_files.py b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/generate_cu_files.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq1_s.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_s.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xs.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq2_xxs.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_s.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq3_xxs.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_nl.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-iq4_xs.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q2_k.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q3_k.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_k.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q4_k.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_1.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q5_k.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q6_k.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q6_k.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q8_0.cu b/llm/llama.cpp/ggml/src/ggml-cuda/template-instances/mmq-instance-q8_0.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/tsembd.cu b/llm/llama.cpp/ggml/src/ggml-cuda/tsembd.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/tsembd.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/tsembd.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/unary.cu b/llm/llama.cpp/ggml/src/ggml-cuda/unary.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/unary.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/unary.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/upscale.cu b/llm/llama.cpp/ggml/src/ggml-cuda/upscale.cu old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/upscale.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/upscale.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/vecdotq.cuh b/llm/llama.cpp/ggml/src/ggml-cuda/vecdotq.cuh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/vendors/cuda.h b/llm/llama.cpp/ggml/src/ggml-cuda/vendors/cuda.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/vendors/hip.h b/llm/llama.cpp/ggml/src/ggml-cuda/vendors/hip.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-cuda/vendors/musa.h b/llm/llama.cpp/ggml/src/ggml-cuda/vendors/musa.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-impl.h b/llm/llama.cpp/ggml/src/ggml-impl.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-kompute.cpp b/llm/llama.cpp/ggml/src/ggml-kompute.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-metal.m b/llm/llama.cpp/ggml/src/ggml-metal.m old mode 100755 new mode 100644 index b512eb0be132e7dfd5dac5d7e4dcee0f1fce5fe9..8740a16c733298386dbd8001604e5a30e108a1ff --- a/llm/llama.cpp/ggml/src/ggml-metal.m +++ b/llm/llama.cpp/ggml/src/ggml-metal.m @@ -1545,27 +1545,23 @@ static enum ggml_status ggml_metal_graph_compute( // to the matrix-vector kernel int ne11_mm_min = 1; -#if 0 // the numbers below are measured on M2 Ultra for 7B and 13B models // these numbers do not translate to other devices or model sizes // TODO: need to find a better approach - if ([ctx->device.name isEqualToString:@"Apple M2 Ultra"]) { - switch (src0t) { - case GGML_TYPE_F16: ne11_mm_min = 2; break; - case GGML_TYPE_Q8_0: ne11_mm_min = 7; break; - case GGML_TYPE_Q2_K: ne11_mm_min = 15; break; - case GGML_TYPE_Q3_K: ne11_mm_min = 7; break; - case GGML_TYPE_Q4_0: - case GGML_TYPE_Q4_1: ne11_mm_min = 15; break; - case GGML_TYPE_Q4_K: ne11_mm_min = 11; break; - case GGML_TYPE_Q5_0: // not tested yet - case GGML_TYPE_Q5_1: ne11_mm_min = 13; break; // not tested yet - case GGML_TYPE_Q5_K: ne11_mm_min = 7; break; - case GGML_TYPE_Q6_K: ne11_mm_min = 7; break; - default: ne11_mm_min = 1; break; - } + switch (src0t) { + case GGML_TYPE_F16: ne11_mm_min = 2; break; + case GGML_TYPE_Q8_0: ne11_mm_min = 7; break; + case GGML_TYPE_Q2_K: ne11_mm_min = 15; break; + case GGML_TYPE_Q3_K: ne11_mm_min = 7; break; + case GGML_TYPE_Q4_0: + case GGML_TYPE_Q4_1: ne11_mm_min = 15; break; + case GGML_TYPE_Q4_K: ne11_mm_min = 11; break; + case GGML_TYPE_Q5_0: // not tested yet + case GGML_TYPE_Q5_1: ne11_mm_min = 13; break; // not tested yet + case GGML_TYPE_Q5_K: ne11_mm_min = 7; break; + case GGML_TYPE_Q6_K: ne11_mm_min = 7; break; + default: ne11_mm_min = 1; break; } -#endif // for now the matrix-matrix multiplication kernel only works on A14+/M1+ SoCs // AMD GPU and older A-chips will reuse matrix-vector multiplication kernel diff --git a/llm/llama.cpp/ggml/src/ggml-quants.c b/llm/llama.cpp/ggml/src/ggml-quants.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-quants.h b/llm/llama.cpp/ggml/src/ggml-quants.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-rpc.cpp b/llm/llama.cpp/ggml/src/ggml-rpc.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl.cpp b/llm/llama.cpp/ggml/src/ggml-sycl.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/backend.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/backend.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/common.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/common.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/common.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/common.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/concat.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/concat.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/concat.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/concat.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/conv.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/conv.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/conv.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/conv.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/convert.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/convert.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/convert.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/convert.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/dequantize.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/dequantize.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/dmmv.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/dmmv.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/dmmv.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/dmmv.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/dpct/helper.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/dpct/helper.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/mmq.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/mmq.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/mmq.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/mmq.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/mmvq.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/mmvq.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/mmvq.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/mmvq.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/norm.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/norm.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/norm.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/norm.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/presets.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/presets.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/rope.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/rope.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/rope.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/rope.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/softmax.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/softmax.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/softmax.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/softmax.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/tsembd.cpp b/llm/llama.cpp/ggml/src/ggml-sycl/tsembd.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/tsembd.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/tsembd.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-sycl/vecdotq.hpp b/llm/llama.cpp/ggml/src/ggml-sycl/vecdotq.hpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml-vulkan.cpp b/llm/llama.cpp/ggml/src/ggml-vulkan.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/ggml.c b/llm/llama.cpp/ggml/src/ggml.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/common.comp b/llm/llama.cpp/ggml/src/kompute-shaders/common.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_add.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_add.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_addrow.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_addrow.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f16_f16.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f16_f16.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f16_f32.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f16_f32.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f32_f16.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f32_f16.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f32_f32.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_cpy_f32_f32.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_diagmask.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_diagmask.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_gelu.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_gelu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_f16.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_f16.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_f32.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_f32.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_q4_0.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_q4_0.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_q4_1.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_q4_1.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_q6_k.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_getrows_q6_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_f16.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_f16.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_mat_f32.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_mat_f32.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q4_0.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q4_0.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q4_1.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q4_1.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q6_k.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q6_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q8_0.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mat_q8_0.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mv_q_n.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mv_q_n.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mv_q_n_pre.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_mul_mv_q_n_pre.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_norm.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_norm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_relu.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_relu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_rmsnorm.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_rmsnorm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_rope_f16.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_rope_f16.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_rope_f32.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_rope_f32.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_scale.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_scale.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_scale_8.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_scale_8.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_silu.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_silu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/op_softmax.comp b/llm/llama.cpp/ggml/src/kompute-shaders/op_softmax.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/kompute-shaders/rope_common.comp b/llm/llama.cpp/ggml/src/kompute-shaders/rope_common.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/llamafile/sgemm.cpp b/llm/llama.cpp/ggml/src/llamafile/sgemm.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/llamafile/sgemm.h b/llm/llama.cpp/ggml/src/llamafile/sgemm.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/CMakeLists.txt b/llm/llama.cpp/ggml/src/vulkan-shaders/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/add.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/add.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/argsort.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/argsort.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/clamp.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/clamp.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/concat.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/concat.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/copy.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/copy.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_f32.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_f32.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_funcs.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_funcs.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_head.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_head.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_iq4_nl.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_iq4_nl.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q2_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q2_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q3_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q3_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q4_0.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q4_0.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q4_1.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q4_1.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q4_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q4_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q5_0.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q5_0.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q5_1.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q5_1.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q5_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q5_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q6_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q6_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q8_0.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/dequant_q8_0.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/diag_mask_inf.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/diag_mask_inf.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/div.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/div.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/gelu.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/gelu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/gelu_quick.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/gelu_quick.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/generic_binary_head.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/generic_binary_head.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/generic_head.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/generic_head.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/generic_unary_head.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/generic_unary_head.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/get_rows.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/get_rows.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/get_rows_quant.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/get_rows_quant.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/group_norm.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/group_norm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/im2col.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/im2col.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/leaky_relu.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/leaky_relu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_split_k_reduce.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_split_k_reduce.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_base.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_base.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_nc.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_nc.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_p021.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_p021.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q2_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q2_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q3_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q3_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q4_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q4_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q5_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q5_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q6_k.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mat_vec_q6_k.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mm.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/mul_mm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/norm.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/norm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/pad.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/pad.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/relu.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/relu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/rms_norm.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/rms_norm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/rope_head.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/rope_head.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/rope_neox.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/rope_neox.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/rope_norm.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/rope_norm.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/scale.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/scale.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/silu.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/silu.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/soft_max.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/soft_max.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/square.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/square.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/sum_rows.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/sum_rows.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/tanh.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/tanh.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/timestep_embedding.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/timestep_embedding.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/types.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/types.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/upscale.comp b/llm/llama.cpp/ggml/src/vulkan-shaders/upscale.comp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp b/llm/llama.cpp/ggml/src/vulkan-shaders/vulkan-shaders-gen.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/LICENSE b/llm/llama.cpp/gguf-py/LICENSE old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/README.md b/llm/llama.cpp/gguf-py/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/examples/reader.py b/llm/llama.cpp/gguf-py/examples/reader.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/examples/writer.py b/llm/llama.cpp/gguf-py/examples/writer.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/__init__.py b/llm/llama.cpp/gguf-py/gguf/__init__.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/constants.py b/llm/llama.cpp/gguf-py/gguf/constants.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/gguf.py b/llm/llama.cpp/gguf-py/gguf/gguf.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/gguf_reader.py b/llm/llama.cpp/gguf-py/gguf/gguf_reader.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/gguf_writer.py b/llm/llama.cpp/gguf-py/gguf/gguf_writer.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/lazy.py b/llm/llama.cpp/gguf-py/gguf/lazy.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/metadata.py b/llm/llama.cpp/gguf-py/gguf/metadata.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/py.typed b/llm/llama.cpp/gguf-py/gguf/py.typed old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/quants.py b/llm/llama.cpp/gguf-py/gguf/quants.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/tensor_mapping.py b/llm/llama.cpp/gguf-py/gguf/tensor_mapping.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/utility.py b/llm/llama.cpp/gguf-py/gguf/utility.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/gguf/vocab.py b/llm/llama.cpp/gguf-py/gguf/vocab.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/pyproject.toml b/llm/llama.cpp/gguf-py/pyproject.toml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/scripts/__init__.py b/llm/llama.cpp/gguf-py/scripts/__init__.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/scripts/gguf_convert_endian.py b/llm/llama.cpp/gguf-py/scripts/gguf_convert_endian.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/scripts/gguf_dump.py b/llm/llama.cpp/gguf-py/scripts/gguf_dump.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/scripts/gguf_hash.py b/llm/llama.cpp/gguf-py/scripts/gguf_hash.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/scripts/gguf_new_metadata.py b/llm/llama.cpp/gguf-py/scripts/gguf_new_metadata.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/scripts/gguf_set_metadata.py b/llm/llama.cpp/gguf-py/scripts/gguf_set_metadata.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/tests/__init__.py b/llm/llama.cpp/gguf-py/tests/__init__.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/gguf-py/tests/test_metadata.py b/llm/llama.cpp/gguf-py/tests/test_metadata.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/README.md b/llm/llama.cpp/grammars/README.md old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/arithmetic.gbnf b/llm/llama.cpp/grammars/arithmetic.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/c.gbnf b/llm/llama.cpp/grammars/c.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/chess.gbnf b/llm/llama.cpp/grammars/chess.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/japanese.gbnf b/llm/llama.cpp/grammars/japanese.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/json.gbnf b/llm/llama.cpp/grammars/json.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/json_arr.gbnf b/llm/llama.cpp/grammars/json_arr.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/grammars/list.gbnf b/llm/llama.cpp/grammars/list.gbnf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/include/llama.h b/llm/llama.cpp/include/llama.h old mode 100755 new mode 100644 index f23355a6bc9593e53d5978ff81b381182dcccd61..6072e76ebdcb7a707939573bb238904d564a13dd --- a/llm/llama.cpp/include/llama.h +++ b/llm/llama.cpp/include/llama.h @@ -1178,6 +1178,20 @@ extern "C" { LLAMA_API void llama_dump_timing_info_yaml(FILE * stream, const struct llama_context * ctx); + // Apply a LoRA adapter to a loaded model + // path_base_model is the path to a higher quality model to use as a base for + // the layers modified by the adapter. Can be NULL to use the current loaded model. + // The model needs to be reloaded before applying a new adapter, otherwise the adapter + // will be applied on top of the previous one + // Returns 0 on success + LLAMA_API int32_t llama_model_apply_lora_from_file( + const struct llama_model * model, + const char * path_lora, + float scale, + const char * path_base_model, + int32_t n_threads); + + #ifdef __cplusplus } #endif diff --git a/llm/llama.cpp/media/llama-leader.jpeg b/llm/llama.cpp/media/llama-leader.jpeg old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/media/llama0-banner.png b/llm/llama.cpp/media/llama0-banner.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/media/llama0-logo.png b/llm/llama.cpp/media/llama0-logo.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/media/llama1-banner.png b/llm/llama.cpp/media/llama1-banner.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/media/llama1-logo.png b/llm/llama.cpp/media/llama1-logo.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/media/matmul.png b/llm/llama.cpp/media/matmul.png old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/media/matmul.svg b/llm/llama.cpp/media/matmul.svg old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/.editorconfig b/llm/llama.cpp/models/.editorconfig old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-aquila.gguf b/llm/llama.cpp/models/ggml-vocab-aquila.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-baichuan.gguf b/llm/llama.cpp/models/ggml-vocab-baichuan.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-bert-bge.gguf b/llm/llama.cpp/models/ggml-vocab-bert-bge.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-bert-bge.gguf.inp b/llm/llama.cpp/models/ggml-vocab-bert-bge.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-bert-bge.gguf.out b/llm/llama.cpp/models/ggml-vocab-bert-bge.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-command-r.gguf b/llm/llama.cpp/models/ggml-vocab-command-r.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-command-r.gguf.inp b/llm/llama.cpp/models/ggml-vocab-command-r.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-command-r.gguf.out b/llm/llama.cpp/models/ggml-vocab-command-r.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-deepseek-coder.gguf b/llm/llama.cpp/models/ggml-vocab-deepseek-coder.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-deepseek-coder.gguf.inp b/llm/llama.cpp/models/ggml-vocab-deepseek-coder.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-deepseek-coder.gguf.out b/llm/llama.cpp/models/ggml-vocab-deepseek-coder.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-deepseek-llm.gguf b/llm/llama.cpp/models/ggml-vocab-deepseek-llm.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-deepseek-llm.gguf.inp b/llm/llama.cpp/models/ggml-vocab-deepseek-llm.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-deepseek-llm.gguf.out b/llm/llama.cpp/models/ggml-vocab-deepseek-llm.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-falcon.gguf b/llm/llama.cpp/models/ggml-vocab-falcon.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-falcon.gguf.inp b/llm/llama.cpp/models/ggml-vocab-falcon.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-falcon.gguf.out b/llm/llama.cpp/models/ggml-vocab-falcon.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-gpt-2.gguf b/llm/llama.cpp/models/ggml-vocab-gpt-2.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-gpt-2.gguf.inp b/llm/llama.cpp/models/ggml-vocab-gpt-2.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-gpt-2.gguf.out b/llm/llama.cpp/models/ggml-vocab-gpt-2.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-gpt-neox.gguf b/llm/llama.cpp/models/ggml-vocab-gpt-neox.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-llama-bpe.gguf b/llm/llama.cpp/models/ggml-vocab-llama-bpe.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-llama-bpe.gguf.inp b/llm/llama.cpp/models/ggml-vocab-llama-bpe.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-llama-bpe.gguf.out b/llm/llama.cpp/models/ggml-vocab-llama-bpe.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-llama-spm.gguf b/llm/llama.cpp/models/ggml-vocab-llama-spm.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-llama-spm.gguf.inp b/llm/llama.cpp/models/ggml-vocab-llama-spm.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-llama-spm.gguf.out b/llm/llama.cpp/models/ggml-vocab-llama-spm.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-mpt.gguf b/llm/llama.cpp/models/ggml-vocab-mpt.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-mpt.gguf.inp b/llm/llama.cpp/models/ggml-vocab-mpt.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-mpt.gguf.out b/llm/llama.cpp/models/ggml-vocab-mpt.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-phi-3.gguf b/llm/llama.cpp/models/ggml-vocab-phi-3.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-phi-3.gguf.inp b/llm/llama.cpp/models/ggml-vocab-phi-3.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-phi-3.gguf.out b/llm/llama.cpp/models/ggml-vocab-phi-3.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-qwen2.gguf b/llm/llama.cpp/models/ggml-vocab-qwen2.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-qwen2.gguf.inp b/llm/llama.cpp/models/ggml-vocab-qwen2.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-qwen2.gguf.out b/llm/llama.cpp/models/ggml-vocab-qwen2.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-refact.gguf b/llm/llama.cpp/models/ggml-vocab-refact.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-refact.gguf.inp b/llm/llama.cpp/models/ggml-vocab-refact.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-refact.gguf.out b/llm/llama.cpp/models/ggml-vocab-refact.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-starcoder.gguf b/llm/llama.cpp/models/ggml-vocab-starcoder.gguf old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-starcoder.gguf.inp b/llm/llama.cpp/models/ggml-vocab-starcoder.gguf.inp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/models/ggml-vocab-starcoder.gguf.out b/llm/llama.cpp/models/ggml-vocab-starcoder.gguf.out old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/mypy.ini b/llm/llama.cpp/mypy.ini old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/pocs/CMakeLists.txt b/llm/llama.cpp/pocs/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/pocs/vdot/CMakeLists.txt b/llm/llama.cpp/pocs/vdot/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/pocs/vdot/q8dot.cpp b/llm/llama.cpp/pocs/vdot/q8dot.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/pocs/vdot/vdot.cpp b/llm/llama.cpp/pocs/vdot/vdot.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/poetry.lock b/llm/llama.cpp/poetry.lock old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/LLM-questions.txt b/llm/llama.cpp/prompts/LLM-questions.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/alpaca.txt b/llm/llama.cpp/prompts/alpaca.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/assistant.txt b/llm/llama.cpp/prompts/assistant.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/chat-with-baichuan.txt b/llm/llama.cpp/prompts/chat-with-baichuan.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/chat-with-bob.txt b/llm/llama.cpp/prompts/chat-with-bob.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/chat-with-qwen.txt b/llm/llama.cpp/prompts/chat-with-qwen.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/chat-with-vicuna-v0.txt b/llm/llama.cpp/prompts/chat-with-vicuna-v0.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/chat-with-vicuna-v1.txt b/llm/llama.cpp/prompts/chat-with-vicuna-v1.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/chat.txt b/llm/llama.cpp/prompts/chat.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/dan-modified.txt b/llm/llama.cpp/prompts/dan-modified.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/dan.txt b/llm/llama.cpp/prompts/dan.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/mnemonics.txt b/llm/llama.cpp/prompts/mnemonics.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/parallel-questions.txt b/llm/llama.cpp/prompts/parallel-questions.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/prompts/reason-act.txt b/llm/llama.cpp/prompts/reason-act.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/pyproject.toml b/llm/llama.cpp/pyproject.toml old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/pyrightconfig.json b/llm/llama.cpp/pyrightconfig.json old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements.txt b/llm/llama.cpp/requirements.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-all.txt b/llm/llama.cpp/requirements/requirements-all.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-compare-llama-bench.txt b/llm/llama.cpp/requirements/requirements-compare-llama-bench.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-convert_hf_to_gguf.txt b/llm/llama.cpp/requirements/requirements-convert_hf_to_gguf.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-convert_hf_to_gguf_update.txt b/llm/llama.cpp/requirements/requirements-convert_hf_to_gguf_update.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-convert_legacy_llama.txt b/llm/llama.cpp/requirements/requirements-convert_legacy_llama.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-convert_llama_ggml_to_gguf.txt b/llm/llama.cpp/requirements/requirements-convert_llama_ggml_to_gguf.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-convert_lora_to_gguf.txt b/llm/llama.cpp/requirements/requirements-convert_lora_to_gguf.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-pydantic.txt b/llm/llama.cpp/requirements/requirements-pydantic.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/requirements/requirements-test-tokenizer-random.txt b/llm/llama.cpp/requirements/requirements-test-tokenizer-random.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/build-info.sh b/llm/llama.cpp/scripts/build-info.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/check-requirements.sh b/llm/llama.cpp/scripts/check-requirements.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/ci-run.sh b/llm/llama.cpp/scripts/ci-run.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/compare-commits.sh b/llm/llama.cpp/scripts/compare-commits.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/compare-llama-bench.py b/llm/llama.cpp/scripts/compare-llama-bench.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/debug-test.sh b/llm/llama.cpp/scripts/debug-test.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/gen-authors.sh b/llm/llama.cpp/scripts/gen-authors.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/gen-unicode-data.py b/llm/llama.cpp/scripts/gen-unicode-data.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/get-flags.mk b/llm/llama.cpp/scripts/get-flags.mk old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/get-hellaswag.sh b/llm/llama.cpp/scripts/get-hellaswag.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/get-pg.sh b/llm/llama.cpp/scripts/get-pg.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/get-wikitext-103.sh b/llm/llama.cpp/scripts/get-wikitext-103.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/get-wikitext-2.sh b/llm/llama.cpp/scripts/get-wikitext-2.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/get-winogrande.sh b/llm/llama.cpp/scripts/get-winogrande.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/hf.sh b/llm/llama.cpp/scripts/hf.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/pod-llama.sh b/llm/llama.cpp/scripts/pod-llama.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/qnt-all.sh b/llm/llama.cpp/scripts/qnt-all.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/run-all-perf.sh b/llm/llama.cpp/scripts/run-all-perf.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/run-all-ppl.sh b/llm/llama.cpp/scripts/run-all-ppl.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/run-with-preset.py b/llm/llama.cpp/scripts/run-with-preset.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/server-llm.sh b/llm/llama.cpp/scripts/server-llm.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/sync-ggml-am.sh b/llm/llama.cpp/scripts/sync-ggml-am.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/sync-ggml.last b/llm/llama.cpp/scripts/sync-ggml.last old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/sync-ggml.sh b/llm/llama.cpp/scripts/sync-ggml.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/verify-checksum-models.py b/llm/llama.cpp/scripts/verify-checksum-models.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/scripts/xxd.cmake b/llm/llama.cpp/scripts/xxd.cmake old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/spm-headers/ggml-alloc.h b/llm/llama.cpp/spm-headers/ggml-alloc.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/spm-headers/ggml-backend.h b/llm/llama.cpp/spm-headers/ggml-backend.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/spm-headers/ggml-metal.h b/llm/llama.cpp/spm-headers/ggml-metal.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/spm-headers/ggml.h b/llm/llama.cpp/spm-headers/ggml.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/spm-headers/llama.h b/llm/llama.cpp/spm-headers/llama.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/CMakeLists.txt b/llm/llama.cpp/src/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-grammar.cpp b/llm/llama.cpp/src/llama-grammar.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-grammar.h b/llm/llama.cpp/src/llama-grammar.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-impl.h b/llm/llama.cpp/src/llama-impl.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-sampling.cpp b/llm/llama.cpp/src/llama-sampling.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-sampling.h b/llm/llama.cpp/src/llama-sampling.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-vocab.cpp b/llm/llama.cpp/src/llama-vocab.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama-vocab.h b/llm/llama.cpp/src/llama-vocab.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/llama.cpp b/llm/llama.cpp/src/llama.cpp old mode 100755 new mode 100644 index a7b1c9ebd9e37d1e9017bdec315b86ecd51a738b..6479e121ed5648c6fa60e3f854948682dbd3f4cd --- a/llm/llama.cpp/src/llama.cpp +++ b/llm/llama.cpp/src/llama.cpp @@ -4892,7 +4892,7 @@ static void llm_load_hparams( } break; case LLM_ARCH_PHI3: { - ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa); + ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW, hparams.n_swa, false); ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps); switch (hparams.n_layer) { @@ -5347,16 +5347,7 @@ static void llm_load_vocab( if (vocab.type == LLAMA_VOCAB_TYPE_BPE) { vocab.tokenizer_add_space_prefix = false; vocab.tokenizer_clean_spaces = true; - if (tokenizer_pre.empty()) { - LLAMA_LOG_WARN("%s: missing pre-tokenizer type, using: 'default'\n", __func__); - LLAMA_LOG_WARN("%s: \n", __func__); - LLAMA_LOG_WARN("%s: ************************************ \n", __func__); - LLAMA_LOG_WARN("%s: GENERATION QUALITY WILL BE DEGRADED! \n", __func__); - LLAMA_LOG_WARN("%s: CONSIDER REGENERATING THE MODEL \n", __func__); - LLAMA_LOG_WARN("%s: ************************************ \n", __func__); - LLAMA_LOG_WARN("%s: \n", __func__); - vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; - } else if (tokenizer_pre == "default") { + if (tokenizer_pre == "default") { vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; } else if ( tokenizer_pre == "llama3" || @@ -5443,7 +5434,8 @@ static void llm_load_vocab( tokenizer_pre == "codeshell") { vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_CODESHELL; } else { - throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str())); + LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__); + vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; } } else if (vocab.type == LLAMA_VOCAB_TYPE_SPM) { vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; @@ -7708,7 +7700,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam } } catch (const std::exception & err) { LLAMA_LOG_ERROR("%s: error loading model: %s\n", __func__, err.what()); - return -1; + throw; } return 0; @@ -8592,14 +8584,14 @@ struct llm_build_context { } struct ggml_tensor * build_inp_mean() { - lctx.inp_mean = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_tokens, n_tokens); + lctx.inp_mean = ggml_new_tensor_2d(ctx0, GGML_TYPE_F32, n_tokens, cparams.n_seq_max); cb(lctx.inp_mean, "inp_mean", -1); ggml_set_input(lctx.inp_mean); return lctx.inp_mean; } struct ggml_tensor * build_inp_cls() { - lctx.inp_cls = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens); + lctx.inp_cls = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, cparams.n_seq_max); cb(lctx.inp_cls, "inp_cls", -1); ggml_set_input(lctx.inp_cls); return lctx.inp_cls; @@ -10774,7 +10766,7 @@ struct llm_build_context { struct ggml_tensor * inp_pos = build_inp_pos(); // KQ_mask (mask for 1 head, it will be broadcasted to all heads) - struct ggml_tensor * KQ_mask_swa = build_inp_KQ_mask_swa(); + struct ggml_tensor * KQ_mask = hparams.n_swa > 0 ? build_inp_KQ_mask_swa() : build_inp_KQ_mask(); for (int il = 0; il < n_layer; ++il) { auto residual = inpL; @@ -10832,7 +10824,7 @@ struct llm_build_context { cur = llm_build_kv(ctx0, lctx, kv_self, gf, model.layers[il].wo, model.layers[il].bo, - Kcur, Vcur, Qcur, KQ_mask_swa, n_tokens, kv_head, n_kv, 1.0f, cb, il); + Kcur, Vcur, Qcur, KQ_mask, n_tokens, kv_head, n_kv, 1.0f, cb, il); } if (il == n_layer - 1) { @@ -14154,19 +14146,16 @@ static void llama_set_inputs(llama_context & lctx, const llama_batch & batch) { GGML_ASSERT(ggml_backend_buffer_is_host(lctx.inp_mean->buffer)); float * data = (float *) lctx.inp_mean->data; - memset(lctx.inp_mean->data, 0, n_tokens * n_tokens * ggml_element_size(lctx.inp_mean)); + memset(lctx.inp_mean->data, 0, n_tokens * cparams.n_seq_max * ggml_element_size(lctx.inp_mean)); std::vector sum(n_tokens, 0); for (int i = 0; i < n_tokens; ++i) { const llama_seq_id seq_id = batch.seq_id[i][0]; - - GGML_ASSERT(seq_id < n_tokens && "seq_id cannot be larger than n_tokens with pooling_type == MEAN"); - sum[seq_id] += 1; } - std::vector div(n_tokens, 0.0f); - for (int i = 0; i < n_tokens; ++i) { + std::vector div(cparams.n_seq_max, 0.0f); + for (uint32_t i = 0; i < cparams.n_seq_max; ++i) { const uint64_t s = sum[i]; if (s > 0) { div[i] = 1.0f/float(s); @@ -14186,14 +14175,11 @@ static void llama_set_inputs(llama_context & lctx, const llama_batch & batch) { GGML_ASSERT(ggml_backend_buffer_is_host(lctx.inp_cls->buffer)); uint32_t * data = (uint32_t *) lctx.inp_cls->data; - memset(lctx.inp_cls->data, 0, n_tokens * ggml_element_size(lctx.inp_cls)); + memset(lctx.inp_cls->data, 0, cparams.n_seq_max * ggml_element_size(lctx.inp_cls)); for (int i = 0; i < n_tokens; ++i) { const llama_seq_id seq_id = batch.seq_id[i][0]; const llama_pos pos = batch.pos[i]; - - GGML_ASSERT(seq_id < n_tokens && "seq_id cannot be larger than n_tokens with pooling_type == CLS"); - if (pos == 0) { data[seq_id] = i; } @@ -14356,7 +14342,7 @@ static size_t llama_output_reserve(llama_context & lctx, size_t n_outputs) { const auto n_embd = hparams.n_embd; // TODO: use a per-batch flag for logits presence instead - const bool has_logits = !cparams.embeddings; + const bool has_logits = cparams.causal_attn; const bool has_embd = lctx.is_encoding || (cparams.embeddings && (cparams.pooling_type == LLAMA_POOLING_TYPE_NONE)); const size_t logits_size = has_logits ? n_vocab*n_outputs_max : 0; @@ -14627,17 +14613,25 @@ static int llama_decode_internal( // no output res = nullptr; embd = nullptr; - } else if (cparams.embeddings) { - res = nullptr; // do not extract logits for embedding case - embd = gf->nodes[gf->n_nodes - 1]; - if (strcmp(embd->name, "result_embd_pooled") != 0) { - embd = gf->nodes[gf->n_nodes - 2]; + } + + if (cparams.embeddings) { + for (int i = gf->n_nodes - 1; i >= 0; --i) { + embd = gf->nodes[i]; + if (strcmp(embd->name, "result_embd_pooled") == 0) { + break; + } } GGML_ASSERT(strcmp(embd->name, "result_embd_pooled") == 0 && "missing embeddings tensor"); - } else { + } else { embd = nullptr; // do not extract embeddings when not needed GGML_ASSERT(strcmp(res->name, "result_output") == 0 && "missing result_output tensor"); } + + if (!cparams.causal_attn) { + res = nullptr; // do not extract logits when not needed + } + // LLAMA_LOG_INFO("graph build time: %.3f ms (%d nodes, %d leafs)\n", (ggml_time_us() - t_start_us)/1000.0, gf->n_nodes, gf->n_leafs); ggml_backend_sched_alloc_graph(lctx.sched, gf); @@ -16429,16 +16423,23 @@ struct llama_model * llama_load_model_from_file( } model->rpc_servers.push_back(servers); } - int status = llama_model_load(path_model, *model, params); - GGML_ASSERT(status <= 0); - if (status < 0) { - if (status == -1) { - LLAMA_LOG_ERROR("%s: failed to load model\n", __func__); - } else if (status == -2) { - LLAMA_LOG_INFO("%s: cancelled model load\n", __func__); + + try { + int status = llama_model_load(path_model, *model, params); + GGML_ASSERT(status <= 0); + if (status < 0) { + if (status == -1) { + LLAMA_LOG_ERROR("%s: failed to load model\n", __func__); + } else if (status == -2) { + LLAMA_LOG_INFO("%s: cancelled model load\n", __func__); + } + delete model; + return nullptr; } + } catch (...) { + LLAMA_LOG_ERROR("%s: exception loading model\n", __func__); delete model; - return nullptr; + throw; } return model; @@ -19171,3 +19172,290 @@ void llama_log_callback_default(ggml_log_level level, const char * text, void * fputs(text, stderr); fflush(stderr); } + +static int llama_apply_lora_from_file_internal( + const struct llama_model & model, const char * path_lora, float scale, const char * path_base_model, int n_threads +) { + LLAMA_LOG_INFO("%s: applying lora adapter from '%s' - please wait ...\n", __func__, path_lora); + + const int64_t t_start_lora_us = ggml_time_us(); + + llama_file fin(path_lora, "rb"); + + // verify magic and version + { + uint32_t magic = fin.read_u32(); + if (magic != LLAMA_FILE_MAGIC_GGLA) { + LLAMA_LOG_ERROR("%s: bad file magic\n", __func__); + return 1; + } + + uint32_t format_version = fin.read_u32(); + if (format_version != 1) { + LLAMA_LOG_ERROR("%s: unsupported file version\n", __func__ ); + return 1; + } + } + + int32_t lora_r = fin.read_u32(); + int32_t lora_alpha = fin.read_u32(); + float scaling = scale * (float)lora_alpha / (float)lora_r; + + LLAMA_LOG_INFO("%s: r = %d, alpha = %d, scaling = %.2f\n", __func__, lora_r, lora_alpha, scaling); + + // load base model + std::unique_ptr ml; + if (path_base_model) { + LLAMA_LOG_INFO("%s: loading base model from '%s'\n", __func__, path_base_model); + ml.reset(new llama_model_loader(path_base_model, /*use_mmap*/ true, /*check_tensors*/ false, /*kv_overrides*/ nullptr)); + ml->init_mappings(/*prefetch*/ false); // no prefetching + } + + struct tensor_meta { + std::string name; + ggml_type type; + int32_t ne[2]; + size_t offset; + }; + std::map tensor_meta_map; + + // load all tensor meta + while (true) { + if (fin.tell() == fin.size) { + // eof + break; + } + + int32_t n_dims; + int32_t name_len; + int32_t ftype; + + fin.read_raw(&n_dims, sizeof(n_dims)); + fin.read_raw(&name_len, sizeof(name_len)); + fin.read_raw(&ftype, sizeof(ftype)); + + if (n_dims != 1 && n_dims != 2) { + LLAMA_LOG_ERROR("%s: unsupported tensor dimension %d\n", __func__, n_dims); + return 1; + } + + int32_t ne[2] = { 1, 1 }; + for (int i = 0; i < n_dims; ++i) { + fin.read_raw(&ne[i], sizeof(ne[i])); + } + + std::string name; + { + GGML_ASSERT(name_len < GGML_MAX_NAME); + char buf[GGML_MAX_NAME]; + fin.read_raw(buf, name_len); + name = std::string(buf, name_len); + } + + // check for lora suffix + std::string lora_suffix; + if (name.length() > 6) { + lora_suffix = name.substr(name.length() - 6); + } + if (lora_suffix != ".loraA" && lora_suffix != ".loraB") { + LLAMA_LOG_ERROR("%s: error: '%s' is not a lora tensor\n", __func__, name.c_str()); + return 1; + } + + // tensor type + ggml_type wtype; + switch (ftype) { + case 0: wtype = GGML_TYPE_F32; break; + case 1: wtype = GGML_TYPE_F16; break; + default: + { + LLAMA_LOG_ERROR("%s: invalid tensor data type '%d'\n", + __func__, ftype); + return 1; + } + } + + // data offset + size_t offset = fin.tell(); + offset = (offset + 31) & -32; + + // skip tensor data + fin.seek(offset + ggml_row_size(wtype, ne[0]) * ne[1], SEEK_SET); + + tensor_meta_map.emplace(name, tensor_meta{ name, wtype, { ne[0], ne[1] }, offset }); + } + + bool warned = false; + int n_tensors = 0; + + // apply + ggml_backend_t backend_cpu = ggml_backend_cpu_init(); + if (backend_cpu == nullptr) { + LLAMA_LOG_ERROR("%s: error: failed to initialize cpu backend\n", __func__); + return 1; + } + ggml_backend_cpu_set_n_threads(backend_cpu, n_threads); + + std::vector> read_buf; + for (const auto & it : model.tensors_by_name) { + const std::string & base_name = it.first; + ggml_tensor * model_t = it.second; + + if (tensor_meta_map.find(base_name + ".loraA") == tensor_meta_map.end() || + tensor_meta_map.find(base_name + ".loraB") == tensor_meta_map.end()) { + continue; + } + + tensor_meta & metaA = tensor_meta_map.at(base_name + ".loraA"); + tensor_meta & metaB = tensor_meta_map.at(base_name + ".loraB"); + + ggml_init_params lora_init_params = { + /* .mem_size */ ggml_tensor_overhead()*128 + ggml_graph_overhead(), + /* .mem_buffer */ nullptr, + /* .no_alloc */ true, + }; + ggml_context * lora_ctx = ggml_init(lora_init_params); + if (lora_ctx == nullptr) { + LLAMA_LOG_ERROR("%s: error: failed to initialize lora context\n", __func__); + ggml_backend_free(backend_cpu); + return 1; + } + + // create tensors + ggml_tensor * loraA = ggml_new_tensor_2d(lora_ctx, metaA.type, metaA.ne[0], metaA.ne[1]); + ggml_tensor * loraB = ggml_new_tensor_2d(lora_ctx, metaB.type, metaB.ne[0], metaB.ne[1]); + ggml_set_name(loraA, metaA.name.c_str()); + ggml_set_name(loraB, metaB.name.c_str()); + + ggml_tensor * base_t; + if (ml) { + if (!ml->get_tensor_meta(base_name.c_str())) { + LLAMA_LOG_ERROR("%s: error: tensor '%s' not found in base model\n", __func__, base_name.c_str()); + return 1; + } + base_t = ggml_dup_tensor(lora_ctx, ml->get_tensor_meta(base_name.c_str())); + } else { + base_t = ggml_dup_tensor(lora_ctx, model_t); + } + ggml_set_name(base_t, base_name.c_str()); + + // allocate in backend buffer + ggml_backend_buffer_t lora_buf = ggml_backend_alloc_ctx_tensors_from_buft(lora_ctx, ggml_backend_cpu_buffer_type()); + if (lora_buf == nullptr) { + LLAMA_LOG_ERROR("%s: error: failed to allocate lora tensors\n", __func__); + return 1; + } + + // load tensor data + auto load_tensor = [&read_buf, &fin](const tensor_meta & tensor_meta, ggml_tensor * tensor) { + read_buf.resize(ggml_nbytes(tensor)); + fin.seek(tensor_meta.offset, SEEK_SET); + fin.read_raw(read_buf.data(), ggml_nbytes(tensor)); + ggml_backend_tensor_set(tensor, read_buf.data(), 0, read_buf.size()); + }; + load_tensor(metaA, loraA); + load_tensor(metaB, loraB); + + // load base model tensor data + if (ml) { + ml->load_data_for(base_t); + } else { + ggml_backend_tensor_copy(model_t, base_t); + } + + if (ggml_is_quantized(base_t->type) && !warned) { + LLAMA_LOG_WARN("%s: warning: using a lora adapter with a quantized model may result in poor quality, " + "use a f16 or f32 base model with --lora-base\n", __func__); + warned = true; + } + + if (base_t->ne[0] != loraA->ne[1] || base_t->ne[1] != loraB->ne[1]) { + LLAMA_LOG_ERROR("%s: incompatible tensor dimensions (%" PRId64 " and %" PRId64 ");" + " are you sure that this adapter is for this model?\n", __func__, base_t->ne[0], loraA->ne[1]); + ggml_free(lora_ctx); + ggml_backend_buffer_free(lora_buf); + ggml_backend_free(backend_cpu); + return 1; + } + + auto build_lora_graph = [&]() { + // w = w + BA*s + ggml_tensor * BA = ggml_mul_mat(lora_ctx, loraA, loraB); + ggml_set_name(BA, "BA"); + + if (scaling != 1.0f) { + BA = ggml_scale(lora_ctx, BA, scaling); + ggml_set_name(BA, "BA_scaled"); + } + + ggml_tensor * r; + r = ggml_add_inplace(lora_ctx, base_t, BA); + ggml_set_name(r, "r_add"); + + if (base_t->type != model_t->type) { + // convert the result to the model type + r = ggml_cast(lora_ctx, r, model_t->type); + ggml_set_name(r, "r_cast"); + } + + return r; + }; + + ggml_cgraph * gf = ggml_new_graph(lora_ctx); + ggml_tensor * r = build_lora_graph(); + ggml_build_forward_expand(gf, r); + + ggml_backend_buffer_t graph_buf = ggml_backend_alloc_ctx_tensors_from_buft(lora_ctx, ggml_backend_cpu_buffer_type()); + if (graph_buf == nullptr) { + LLAMA_LOG_ERROR("%s: error: failed to allocate graph tensors\n", __func__); + ggml_free(lora_ctx); + ggml_backend_buffer_free(lora_buf); + ggml_backend_free(backend_cpu); + return 1; + } + + ggml_backend_graph_compute(backend_cpu, gf); + + ggml_backend_tensor_set(model_t, r->data, 0, ggml_nbytes(r)); + +#if 0 + // TODO: use scheduler with fallback to CPU for less copies between CPU and GPU + //ggml_backend_sched_t sched = ggml_backend_sched_new(backends.data(), backends.size(), GGML_DEFAULT_GRAPH_SIZE); + + // sched compute + ggml_build_forward_expand(gf, build_graph()); + ggml_backend_sched_init_measure(sched, gf); + + // create the graph again, since the previous one was destroyed by the measure + ggml_graph_clear(gf); + ggml_build_forward_expand(gf, build_graph()); + ggml_backend_sched_graph_compute(sched, gf); + ggml_backend_sched_free(sched); +#endif + + ggml_backend_buffer_free(lora_buf); + ggml_backend_buffer_free(graph_buf); + ggml_free(lora_ctx); + + n_tensors++; + if (n_tensors % 4 == 0) { + LLAMA_LOG_INFO("."); + } + } + + ggml_backend_free(backend_cpu); + + const int64_t t_lora_us = ggml_time_us() - t_start_lora_us; + LLAMA_LOG_INFO(" done (%.2f ms)\n", t_lora_us / 1000.0); + + return 0; +} + +int32_t llama_model_apply_lora_from_file(const struct llama_model * model, const char * path_lora, float scale, const char * path_base_model, int32_t n_threads) { + try { + return llama_apply_lora_from_file_internal(*model, path_lora, scale, path_base_model, n_threads); + } catch (const std::exception & err) { + LLAMA_LOG_ERROR("%s: failed to apply lora adapter: %s\n", __func__, err.what()); + return 1; + } +} \ No newline at end of file diff --git a/llm/llama.cpp/src/unicode-data.cpp b/llm/llama.cpp/src/unicode-data.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/unicode-data.h b/llm/llama.cpp/src/unicode-data.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/unicode.cpp b/llm/llama.cpp/src/unicode.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/src/unicode.h b/llm/llama.cpp/src/unicode.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/.gitignore b/llm/llama.cpp/tests/.gitignore old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/CMakeLists.txt b/llm/llama.cpp/tests/CMakeLists.txt old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/get-model.cpp b/llm/llama.cpp/tests/get-model.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/get-model.h b/llm/llama.cpp/tests/get-model.h old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/run-json-schema-to-grammar.mjs b/llm/llama.cpp/tests/run-json-schema-to-grammar.mjs old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-autorelease.cpp b/llm/llama.cpp/tests/test-autorelease.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-backend-ops.cpp b/llm/llama.cpp/tests/test-backend-ops.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-c.c b/llm/llama.cpp/tests/test-c.c old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-chat-template.cpp b/llm/llama.cpp/tests/test-chat-template.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-double-float.cpp b/llm/llama.cpp/tests/test-double-float.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-grad0.cpp b/llm/llama.cpp/tests/test-grad0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-grammar-integration.cpp b/llm/llama.cpp/tests/test-grammar-integration.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-grammar-parser.cpp b/llm/llama.cpp/tests/test-grammar-parser.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-json-schema-to-grammar.cpp b/llm/llama.cpp/tests/test-json-schema-to-grammar.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-llama-grammar.cpp b/llm/llama.cpp/tests/test-llama-grammar.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-model-load-cancel.cpp b/llm/llama.cpp/tests/test-model-load-cancel.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-opt.cpp b/llm/llama.cpp/tests/test-opt.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-quantize-fns.cpp b/llm/llama.cpp/tests/test-quantize-fns.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-quantize-perf.cpp b/llm/llama.cpp/tests/test-quantize-perf.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-rope.cpp b/llm/llama.cpp/tests/test-rope.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-sampling.cpp b/llm/llama.cpp/tests/test-sampling.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-tokenizer-0.cpp b/llm/llama.cpp/tests/test-tokenizer-0.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-tokenizer-0.py b/llm/llama.cpp/tests/test-tokenizer-0.py old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-tokenizer-0.sh b/llm/llama.cpp/tests/test-tokenizer-0.sh old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-tokenizer-1-bpe.cpp b/llm/llama.cpp/tests/test-tokenizer-1-bpe.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-tokenizer-1-spm.cpp b/llm/llama.cpp/tests/test-tokenizer-1-spm.cpp old mode 100755 new mode 100644 diff --git a/llm/llama.cpp/tests/test-tokenizer-random.py b/llm/llama.cpp/tests/test-tokenizer-random.py old mode 100755 new mode 100644 diff --git a/llm/llm.go b/llm/llm.go old mode 100755 new mode 100644 diff --git a/llm/llm_darwin_amd64.go b/llm/llm_darwin_amd64.go old mode 100755 new mode 100644 diff --git a/llm/llm_darwin_arm64.go b/llm/llm_darwin_arm64.go old mode 100755 new mode 100644 diff --git a/llm/llm_linux.go b/llm/llm_linux.go old mode 100755 new mode 100644 diff --git a/llm/llm_windows.go b/llm/llm_windows.go old mode 100755 new mode 100644 diff --git a/llm/memory.go b/llm/memory.go old mode 100755 new mode 100644 diff --git a/llm/memory_test.go b/llm/memory_test.go old mode 100755 new mode 100644 diff --git a/llm/patches/01-load-progress.diff b/llm/patches/01-load-progress.diff old mode 100755 new mode 100644 diff --git a/llm/patches/02-clip-log.diff b/llm/patches/02-clip-log.diff old mode 100755 new mode 100644 diff --git a/llm/patches/03-load_exception.diff b/llm/patches/03-load_exception.diff old mode 100755 new mode 100644 diff --git a/llm/patches/04-metal.diff b/llm/patches/04-metal.diff old mode 100755 new mode 100644 diff --git a/llm/patches/05-default-pretokenizer.diff b/llm/patches/05-default-pretokenizer.diff old mode 100755 new mode 100644 diff --git a/llm/patches/06-embeddings.diff b/llm/patches/06-embeddings.diff old mode 100755 new mode 100644 diff --git a/llm/patches/07-clip-unicode.diff b/llm/patches/07-clip-unicode.diff old mode 100755 new mode 100644 diff --git a/llm/patches/08-pooling.diff b/llm/patches/08-pooling.diff old mode 100755 new mode 100644 diff --git a/llm/patches/09-lora.diff b/llm/patches/09-lora.diff old mode 100755 new mode 100644 diff --git a/llm/patches/11-phi3-sliding-window.diff b/llm/patches/11-phi3-sliding-window.diff old mode 100755 new mode 100644 diff --git a/llm/payload.go b/llm/payload.go old mode 100755 new mode 100644 diff --git a/llm/server.go b/llm/server.go old mode 100755 new mode 100644 diff --git a/llm/status.go b/llm/status.go old mode 100755 new mode 100644 diff --git a/macapp/.eslintrc.json b/macapp/.eslintrc.json old mode 100755 new mode 100644 diff --git a/macapp/.gitignore b/macapp/.gitignore old mode 100755 new mode 100644 diff --git a/macapp/README.md b/macapp/README.md old mode 100755 new mode 100644 diff --git a/macapp/assets/icon.icns b/macapp/assets/icon.icns old mode 100755 new mode 100644 diff --git a/macapp/assets/iconDarkTemplate.png b/macapp/assets/iconDarkTemplate.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconDarkTemplate@2x.png b/macapp/assets/iconDarkTemplate@2x.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconDarkUpdateTemplate.png b/macapp/assets/iconDarkUpdateTemplate.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconDarkUpdateTemplate@2x.png b/macapp/assets/iconDarkUpdateTemplate@2x.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconTemplate.png b/macapp/assets/iconTemplate.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconTemplate@2x.png b/macapp/assets/iconTemplate@2x.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconUpdateTemplate.png b/macapp/assets/iconUpdateTemplate.png old mode 100755 new mode 100644 diff --git a/macapp/assets/iconUpdateTemplate@2x.png b/macapp/assets/iconUpdateTemplate@2x.png old mode 100755 new mode 100644 diff --git a/macapp/forge.config.ts b/macapp/forge.config.ts old mode 100755 new mode 100644 diff --git a/macapp/package-lock.json b/macapp/package-lock.json old mode 100755 new mode 100644 diff --git a/macapp/package.json b/macapp/package.json old mode 100755 new mode 100644 diff --git a/macapp/postcss.config.js b/macapp/postcss.config.js old mode 100755 new mode 100644 diff --git a/macapp/src/app.css b/macapp/src/app.css old mode 100755 new mode 100644 diff --git a/macapp/src/app.tsx b/macapp/src/app.tsx old mode 100755 new mode 100644 diff --git a/macapp/src/declarations.d.ts b/macapp/src/declarations.d.ts old mode 100755 new mode 100644 diff --git a/macapp/src/index.html b/macapp/src/index.html old mode 100755 new mode 100644 diff --git a/macapp/src/index.ts b/macapp/src/index.ts old mode 100755 new mode 100644 diff --git a/macapp/src/install.ts b/macapp/src/install.ts old mode 100755 new mode 100644 diff --git a/macapp/src/ollama.svg b/macapp/src/ollama.svg old mode 100755 new mode 100644 diff --git a/macapp/src/preload.ts b/macapp/src/preload.ts old mode 100755 new mode 100644 diff --git a/macapp/src/renderer.tsx b/macapp/src/renderer.tsx old mode 100755 new mode 100644 diff --git a/macapp/tailwind.config.js b/macapp/tailwind.config.js old mode 100755 new mode 100644 diff --git a/macapp/tsconfig.json b/macapp/tsconfig.json old mode 100755 new mode 100644 diff --git a/macapp/webpack.main.config.ts b/macapp/webpack.main.config.ts old mode 100755 new mode 100644 diff --git a/macapp/webpack.plugins.ts b/macapp/webpack.plugins.ts old mode 100755 new mode 100644 diff --git a/macapp/webpack.renderer.config.ts b/macapp/webpack.renderer.config.ts old mode 100755 new mode 100644 diff --git a/macapp/webpack.rules.ts b/macapp/webpack.rules.ts old mode 100755 new mode 100644 diff --git a/main.go b/main.go old mode 100755 new mode 100644 diff --git a/openai/openai.go b/openai/openai.go old mode 100755 new mode 100644 diff --git a/openai/openai_test.go b/openai/openai_test.go old mode 100755 new mode 100644 diff --git a/parser/parser.go b/parser/parser.go old mode 100755 new mode 100644 diff --git a/parser/parser_test.go b/parser/parser_test.go old mode 100755 new mode 100644 diff --git a/progress/bar.go b/progress/bar.go old mode 100755 new mode 100644 diff --git a/progress/progress.go b/progress/progress.go old mode 100755 new mode 100644 diff --git a/progress/spinner.go b/progress/spinner.go old mode 100755 new mode 100644 diff --git a/readline/buffer.go b/readline/buffer.go old mode 100755 new mode 100644 diff --git a/readline/errors.go b/readline/errors.go old mode 100755 new mode 100644 diff --git a/readline/history.go b/readline/history.go old mode 100755 new mode 100644 diff --git a/readline/readline.go b/readline/readline.go old mode 100755 new mode 100644 diff --git a/readline/readline_unix.go b/readline/readline_unix.go old mode 100755 new mode 100644 diff --git a/readline/readline_windows.go b/readline/readline_windows.go old mode 100755 new mode 100644 diff --git a/readline/term.go b/readline/term.go old mode 100755 new mode 100644 diff --git a/readline/term_bsd.go b/readline/term_bsd.go old mode 100755 new mode 100644 diff --git a/readline/term_linux.go b/readline/term_linux.go old mode 100755 new mode 100644 diff --git a/readline/term_windows.go b/readline/term_windows.go old mode 100755 new mode 100644 diff --git a/readline/types.go b/readline/types.go old mode 100755 new mode 100644 diff --git a/scripts/build.sh b/scripts/build.sh old mode 100755 new mode 100644 diff --git a/scripts/build_darwin.sh b/scripts/build_darwin.sh old mode 100755 new mode 100644 diff --git a/scripts/build_docker.sh b/scripts/build_docker.sh old mode 100755 new mode 100644 diff --git a/scripts/build_linux.sh b/scripts/build_linux.sh old mode 100755 new mode 100644 diff --git a/scripts/build_remote.py b/scripts/build_remote.py old mode 100755 new mode 100644 diff --git a/scripts/build_windows.ps1 b/scripts/build_windows.ps1 old mode 100755 new mode 100644 diff --git a/scripts/install.sh b/scripts/install.sh old mode 100755 new mode 100644 diff --git a/scripts/publish.sh b/scripts/publish.sh old mode 100755 new mode 100644 diff --git a/scripts/push_docker.sh b/scripts/push_docker.sh old mode 100755 new mode 100644 diff --git a/scripts/rh_linux_deps.sh b/scripts/rh_linux_deps.sh old mode 100755 new mode 100644 diff --git a/scripts/tag_latest.sh b/scripts/tag_latest.sh old mode 100755 new mode 100644 diff --git a/server/auth.go b/server/auth.go old mode 100755 new mode 100644 diff --git a/server/download.go b/server/download.go old mode 100755 new mode 100644 diff --git a/server/fixblobs.go b/server/fixblobs.go old mode 100755 new mode 100644 diff --git a/server/fixblobs_test.go b/server/fixblobs_test.go old mode 100755 new mode 100644 diff --git a/server/images.go b/server/images.go old mode 100755 new mode 100644 diff --git a/server/layer.go b/server/layer.go old mode 100755 new mode 100644 diff --git a/server/manifest.go b/server/manifest.go old mode 100755 new mode 100644 diff --git a/server/manifest_test.go b/server/manifest_test.go old mode 100755 new mode 100644 diff --git a/server/model.go b/server/model.go old mode 100755 new mode 100644 diff --git a/server/model_test.go b/server/model_test.go old mode 100755 new mode 100644 diff --git a/server/modelpath.go b/server/modelpath.go old mode 100755 new mode 100644 diff --git a/server/modelpath_test.go b/server/modelpath_test.go old mode 100755 new mode 100644 diff --git a/server/prompt.go b/server/prompt.go old mode 100755 new mode 100644 diff --git a/server/prompt_test.go b/server/prompt_test.go old mode 100755 new mode 100644 diff --git a/server/routes.go b/server/routes.go old mode 100755 new mode 100644 diff --git a/server/routes_create_test.go b/server/routes_create_test.go old mode 100755 new mode 100644 diff --git a/server/routes_delete_test.go b/server/routes_delete_test.go old mode 100755 new mode 100644 diff --git a/server/routes_generate_test.go b/server/routes_generate_test.go old mode 100755 new mode 100644 diff --git a/server/routes_list_test.go b/server/routes_list_test.go old mode 100755 new mode 100644 diff --git a/server/routes_test.go b/server/routes_test.go old mode 100755 new mode 100644 diff --git a/server/sched.go b/server/sched.go old mode 100755 new mode 100644 diff --git a/server/sched_test.go b/server/sched_test.go old mode 100755 new mode 100644 diff --git a/server/sparse_common.go b/server/sparse_common.go old mode 100755 new mode 100644 diff --git a/server/sparse_windows.go b/server/sparse_windows.go old mode 100755 new mode 100644 diff --git a/server/testdata/tools/command-r-plus.gotmpl b/server/testdata/tools/command-r-plus.gotmpl old mode 100755 new mode 100644 diff --git a/server/testdata/tools/command-r-plus.out b/server/testdata/tools/command-r-plus.out old mode 100755 new mode 100644 diff --git a/server/testdata/tools/firefunction.gotmpl b/server/testdata/tools/firefunction.gotmpl old mode 100755 new mode 100644 diff --git a/server/testdata/tools/firefunction.out b/server/testdata/tools/firefunction.out old mode 100755 new mode 100644 diff --git a/server/testdata/tools/llama3-groq-tool-use.gotmpl b/server/testdata/tools/llama3-groq-tool-use.gotmpl old mode 100755 new mode 100644 diff --git a/server/testdata/tools/llama3-groq-tool-use.out b/server/testdata/tools/llama3-groq-tool-use.out old mode 100755 new mode 100644 diff --git a/server/testdata/tools/messages.json b/server/testdata/tools/messages.json old mode 100755 new mode 100644 diff --git a/server/testdata/tools/mistral.gotmpl b/server/testdata/tools/mistral.gotmpl old mode 100755 new mode 100644 diff --git a/server/testdata/tools/mistral.out b/server/testdata/tools/mistral.out old mode 100755 new mode 100644 diff --git a/server/testdata/tools/tools.json b/server/testdata/tools/tools.json old mode 100755 new mode 100644 diff --git a/server/testdata/tools/xlam.gotmpl b/server/testdata/tools/xlam.gotmpl old mode 100755 new mode 100644 diff --git a/server/testdata/tools/xlam.out b/server/testdata/tools/xlam.out old mode 100755 new mode 100644 diff --git a/server/upload.go b/server/upload.go old mode 100755 new mode 100644 diff --git a/template/alfred.gotmpl b/template/alfred.gotmpl old mode 100755 new mode 100644 diff --git a/template/alfred.json b/template/alfred.json old mode 100755 new mode 100644 diff --git a/template/alpaca.gotmpl b/template/alpaca.gotmpl old mode 100755 new mode 100644 diff --git a/template/alpaca.json b/template/alpaca.json old mode 100755 new mode 100644 diff --git a/template/chatml.gotmpl b/template/chatml.gotmpl old mode 100755 new mode 100644 diff --git a/template/chatml.json b/template/chatml.json old mode 100755 new mode 100644 diff --git a/template/chatqa.gotmpl b/template/chatqa.gotmpl old mode 100755 new mode 100644 diff --git a/template/chatqa.json b/template/chatqa.json old mode 100755 new mode 100644 diff --git a/template/codellama-70b-instruct.gotmpl b/template/codellama-70b-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/codellama-70b-instruct.json b/template/codellama-70b-instruct.json old mode 100755 new mode 100644 diff --git a/template/falcon-instruct.gotmpl b/template/falcon-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/falcon-instruct.json b/template/falcon-instruct.json old mode 100755 new mode 100644 diff --git a/template/gemma-instruct.gotmpl b/template/gemma-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/gemma-instruct.json b/template/gemma-instruct.json old mode 100755 new mode 100644 diff --git a/template/granite-instruct.gotmpl b/template/granite-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/granite-instruct.json b/template/granite-instruct.json old mode 100755 new mode 100644 diff --git a/template/index.json b/template/index.json old mode 100755 new mode 100644 diff --git a/template/llama2-chat.gotmpl b/template/llama2-chat.gotmpl old mode 100755 new mode 100644 diff --git a/template/llama2-chat.json b/template/llama2-chat.json old mode 100755 new mode 100644 diff --git a/template/llama3-instruct.gotmpl b/template/llama3-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/llama3-instruct.json b/template/llama3-instruct.json old mode 100755 new mode 100644 diff --git a/template/magicoder.gotmpl b/template/magicoder.gotmpl old mode 100755 new mode 100644 diff --git a/template/magicoder.json b/template/magicoder.json old mode 100755 new mode 100644 diff --git a/template/mistral-instruct.gotmpl b/template/mistral-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/mistral-instruct.json b/template/mistral-instruct.json old mode 100755 new mode 100644 diff --git a/template/openchat.gotmpl b/template/openchat.gotmpl old mode 100755 new mode 100644 diff --git a/template/openchat.json b/template/openchat.json old mode 100755 new mode 100644 diff --git a/template/phi-3.gotmpl b/template/phi-3.gotmpl old mode 100755 new mode 100644 diff --git a/template/phi-3.json b/template/phi-3.json old mode 100755 new mode 100644 diff --git a/template/solar-instruct.gotmpl b/template/solar-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/solar-instruct.json b/template/solar-instruct.json old mode 100755 new mode 100644 diff --git a/template/starcoder2-instruct.gotmpl b/template/starcoder2-instruct.gotmpl old mode 100755 new mode 100644 diff --git a/template/starcoder2-instruct.json b/template/starcoder2-instruct.json old mode 100755 new mode 100644 diff --git a/template/template.go b/template/template.go old mode 100755 new mode 100644 diff --git a/template/template_test.go b/template/template_test.go old mode 100755 new mode 100644 diff --git a/template/testdata/alfred.gotmpl/system-user-assistant-user b/template/testdata/alfred.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/alfred.gotmpl/user b/template/testdata/alfred.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/alfred.gotmpl/user-assistant-user b/template/testdata/alfred.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/alpaca.gotmpl/system-user-assistant-user b/template/testdata/alpaca.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/alpaca.gotmpl/user b/template/testdata/alpaca.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/alpaca.gotmpl/user-assistant-user b/template/testdata/alpaca.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/chatml.gotmpl/system-user-assistant-user b/template/testdata/chatml.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/chatml.gotmpl/user b/template/testdata/chatml.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/chatml.gotmpl/user-assistant-user b/template/testdata/chatml.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/chatqa.gotmpl/system-user-assistant-user b/template/testdata/chatqa.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/chatqa.gotmpl/user b/template/testdata/chatqa.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/chatqa.gotmpl/user-assistant-user b/template/testdata/chatqa.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/codellama-70b-instruct.gotmpl/system-user-assistant-user b/template/testdata/codellama-70b-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/codellama-70b-instruct.gotmpl/user b/template/testdata/codellama-70b-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/codellama-70b-instruct.gotmpl/user-assistant-user b/template/testdata/codellama-70b-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/falcon-instruct.gotmpl/system-user-assistant-user b/template/testdata/falcon-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/falcon-instruct.gotmpl/user b/template/testdata/falcon-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/falcon-instruct.gotmpl/user-assistant-user b/template/testdata/falcon-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/gemma-instruct.gotmpl/system-user-assistant-user b/template/testdata/gemma-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/gemma-instruct.gotmpl/user b/template/testdata/gemma-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/gemma-instruct.gotmpl/user-assistant-user b/template/testdata/gemma-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/granite-instruct.gotmpl/system-user-assistant-user b/template/testdata/granite-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/granite-instruct.gotmpl/user b/template/testdata/granite-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/granite-instruct.gotmpl/user-assistant-user b/template/testdata/granite-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/llama2-chat.gotmpl/system-user-assistant-user b/template/testdata/llama2-chat.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/llama2-chat.gotmpl/user b/template/testdata/llama2-chat.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/llama2-chat.gotmpl/user-assistant-user b/template/testdata/llama2-chat.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/llama3-instruct.gotmpl/system-user-assistant-user b/template/testdata/llama3-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/llama3-instruct.gotmpl/user b/template/testdata/llama3-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/llama3-instruct.gotmpl/user-assistant-user b/template/testdata/llama3-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/magicoder.gotmpl/system-user-assistant-user b/template/testdata/magicoder.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/magicoder.gotmpl/user b/template/testdata/magicoder.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/magicoder.gotmpl/user-assistant-user b/template/testdata/magicoder.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/mistral-instruct.gotmpl/system-user-assistant-user b/template/testdata/mistral-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/mistral-instruct.gotmpl/user b/template/testdata/mistral-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/mistral-instruct.gotmpl/user-assistant-user b/template/testdata/mistral-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/openchat.gotmpl/system-user-assistant-user b/template/testdata/openchat.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/openchat.gotmpl/user b/template/testdata/openchat.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/openchat.gotmpl/user-assistant-user b/template/testdata/openchat.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/phi-3.gotmpl/system-user-assistant-user b/template/testdata/phi-3.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/phi-3.gotmpl/user b/template/testdata/phi-3.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/phi-3.gotmpl/user-assistant-user b/template/testdata/phi-3.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/solar-instruct.gotmpl/system-user-assistant-user b/template/testdata/solar-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/solar-instruct.gotmpl/user b/template/testdata/solar-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/solar-instruct.gotmpl/user-assistant-user b/template/testdata/solar-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/starcoder2-instruct.gotmpl/system-user-assistant-user b/template/testdata/starcoder2-instruct.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/starcoder2-instruct.gotmpl/user b/template/testdata/starcoder2-instruct.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/starcoder2-instruct.gotmpl/user-assistant-user b/template/testdata/starcoder2-instruct.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/templates.jsonl b/template/testdata/templates.jsonl old mode 100755 new mode 100644 diff --git a/template/testdata/vicuna.gotmpl/system-user-assistant-user b/template/testdata/vicuna.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/vicuna.gotmpl/user b/template/testdata/vicuna.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/vicuna.gotmpl/user-assistant-user b/template/testdata/vicuna.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/zephyr.gotmpl/system-user-assistant-user b/template/testdata/zephyr.gotmpl/system-user-assistant-user old mode 100755 new mode 100644 diff --git a/template/testdata/zephyr.gotmpl/user b/template/testdata/zephyr.gotmpl/user old mode 100755 new mode 100644 diff --git a/template/testdata/zephyr.gotmpl/user-assistant-user b/template/testdata/zephyr.gotmpl/user-assistant-user old mode 100755 new mode 100644 diff --git a/template/vicuna.gotmpl b/template/vicuna.gotmpl old mode 100755 new mode 100644 diff --git a/template/vicuna.json b/template/vicuna.json old mode 100755 new mode 100644 diff --git a/template/zephyr.gotmpl b/template/zephyr.gotmpl old mode 100755 new mode 100644 diff --git a/template/zephyr.json b/template/zephyr.json old mode 100755 new mode 100644 diff --git a/types/errtypes/errtypes.go b/types/errtypes/errtypes.go old mode 100755 new mode 100644 diff --git a/types/model/name.go b/types/model/name.go old mode 100755 new mode 100644 diff --git a/types/model/name_test.go b/types/model/name_test.go old mode 100755 new mode 100644 diff --git a/types/model/testdata/fuzz/FuzzName/d37463aa416f6bab b/types/model/testdata/fuzz/FuzzName/d37463aa416f6bab old mode 100755 new mode 100644 diff --git a/util/bufioutil/buffer_seeker.go b/util/bufioutil/buffer_seeker.go old mode 100755 new mode 100644 diff --git a/util/bufioutil/buffer_seeker_test.go b/util/bufioutil/buffer_seeker_test.go old mode 100755 new mode 100644 diff --git a/version/version.go b/version/version.go old mode 100755 new mode 100644