Skip to content

GitLab

Commit 27a7ad86 authored by luopl's avatar luopl
Browse files

update to v0.9.1

parent 731cf9b8
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 1399 additions and 251 deletions
.env.local 0 → 100644
View file @ 27a7ad86
# Note: actually we do not support .env, just for reference
# api
API_HOST=0.0.0.0
API_PORT=8000
API_KEY=
API_MODEL_NAME=gpt-3.5-turbo
FASTAPI_ROOT_PATH=
# general
DISABLE_VERSION_CHECK=
FORCE_CHECK_IMPORTS=
LLAMAFACTORY_VERBOSITY=
USE_MODELSCOPE_HUB=
RECORD_VRAM=
# torchrun
FORCE_TORCHRUN=
MASTER_ADDR=
MASTER_PORT=
NNODES=
RANK=
NPROC_PER_NODE=
# wandb
WANDB_DISABLED=
WANDB_PROJECT=huggingface
WANDB_API_KEY=
# gradio ui
GRADIO_SHARE=False
GRADIO_SERVER_NAME=0.0.0.0
GRADIO_SERVER_PORT=
GRADIO_ROOT_PATH=
# setup
ENABLE_SHORT_CONSOLE=1
# reserved (do not use)
LLAMABOARD_ENABLED=
LLAMABOARD_WORKDIR=
Makefile
View file @ 27a7ad86
.PHONY: quality style test
check_dirs := scripts src tests
check_dirs := scripts src tests setup.py
quality:
ruff check $(check_dirs)
......
README.md
View file @ 27a7ad86
This diff is collapsed.
README_zh.md
View file @ 27a7ad86
......@@ -26,11 +26,14 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
选择你的打开方式：
- **Colab**：https://colab.research.google.com/drive/1d5KQtbemerlSDSxZIfAaWXhKr30QypiK?usp=sharing
- **PAI-DSW**：https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory
- **PAI-DSW**：[Llama3 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory) | [Qwen2-VL 案例](https://gallery.pai-ml.com/#/preview/deepLearning/nlp/llama_factory_qwen2vl)
- **本地机器**：请见[如何使用](#如何使用)
- **入门教程**：https://zhuanlan.zhihu.com/p/695287607
- **框架文档**：https://llamafactory.readthedocs.io/zh-cn/latest/
> [!NOTE]
> 除上述链接以外的其他网站均为未经许可的第三方网站，请小心甄别。
## 目录
- [项目特色](#项目特色)
......@@ -48,11 +51,11 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 项目特色
- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
- **多种模型**：LLaMA、LLaVA、Mistral、Mixtral-MoE、Qwen、Qwen2-VL、Yi、Gemma、Baichuan、ChatGLM、Phi 等等。
- **集成方法**：（增量）预训练、（多模态）指令监督微调、奖励模型训练、PPO 训练、DPO 训练、KTO 训练、ORPO 训练等等。
- **多种精度**：16 比特全参数微调、冻结微调、LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ 的 2/3/4/5/6/8 比特 QLoRA 微调。
- **先进算法**：GaLore、BAdam、Adam-mini、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
- **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune 和 rsLoRA。
- **先进算法**：[GaLore](https://github.com/jiaweizzhao/GaLore)、[BAdam](https://github.com/Ledzy/BAdam)、[Adam-mini](https://github.com/zyushun/Adam-mini)、DoRA、LongLoRA、LLaMA Pro、Mixture-of-Depths、LoRA+、LoftQ、PiSSA 和 Agent 微调。
- **实用技巧**：[FlashAttention-2](https://github.com/Dao-AILab/flash-attention)、[Unsloth](https://github.com/unslothai/unsloth)、[Liger Kernel](https://github.com/linkedin/Liger-Kernel)、RoPE scaling、NEFTune 和 rsLoRA。
- **实验监控**：LlamaBoard、TensorBoard、Wandb、MLflow 等等。
- **极速推理**：基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。
......@@ -73,19 +76,25 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 更新日志
[24/08/09] 我们支持了 **[Adam-mini](https://arxiv.org/abs/2406.16793)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。
[24/09/19] 我们支持了 **[Qwen2.5](https://qwenlm.github.io/blog/qwen2.5/)** 模型的微调。
[24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。
[24/08/30] 我们支持了 **[Qwen2-VL](https://qwenlm.github.io/blog/qwen2-vl/)** 模型的微调。感谢 [@simonJJJ](https://github.com/simonJJJ) 的 PR。
[24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。
[24/08/27] 我们支持了 **[Liger Kernel](https://github.com/linkedin/Liger-Kernel)**。请使用 `enable_liger_kernel: true` 来加速训练。
[24/08/09] 我们支持了 **[Adam-mini](https://github.com/zyushun/Adam-mini)** 优化器。详细用法请参照 [examples](examples/README_zh.md)。感谢 [@relic-yuexi](https://github.com/relic-yuexi) 的 PR。
<details><summary>展开日志</summary>
[24/07/04] 我们支持了[无污染打包训练](https://github.com/MeetKai/functionary/tree/main/functionary/train/packing)。请使用 `neat_packing: true` 参数。感谢 [@chuan298](https://github.com/chuan298) 的 PR。
[24/06/16] 我们支持了 **[PiSSA](https://arxiv.org/abs/2404.02948)** 算法。详细用法请参照 [examples](examples/README_zh.md)。
[24/06/07] 我们支持了 **[Qwen2](https://qwenlm.github.io/blog/qwen2/)** 和 **[GLM-4](https://github.com/THUDM/GLM-4)** 模型的微调。
[24/05/26] 我们支持了 **[SimPO](https://arxiv.org/abs/2405.14734)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。
[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `gemma` 模板进行微调使其获得对话能力。
[24/05/20] 我们支持了 **PaliGemma** 系列模型的微调。注意 PaliGemma 是预训练模型，你需要使用 `paligemma` 模板进行微调使其获得对话能力。
[24/05/18] 我们支持了 **[KTO](https://arxiv.org/abs/2402.01306)** 偏好对齐算法。详细用法请参照 [examples](examples/README_zh.md)。
......@@ -157,33 +166,36 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 模型
| 模型名 | 模型大小 | Template |
| ----------------------------------------------------------------- | -------------------------------- | --------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - |
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |
| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 |
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |
| [Llama 3/Llama 3.1](https://huggingface.co/meta-llama) | 8B/70B | llama3 |
| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | vicuna |
| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B | cpm |
| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral |
| [OLMo](https://huggingface.co/allenai) | 1B/7B | - |
| [PaliGemma](https://huggingface.co/google) | 3B | gemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - |
| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi |
| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |
| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse |
| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi |
| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl |
| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan |
| 模型名 | 模型大小 | Template |
| ----------------------------------------------------------------- | -------------------------------- | ---------------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - |
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |
| [InternLM2/InternLM2.5](https://huggingface.co/internlm) | 7B/20B | intern2 |
| [Llama](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | - |
| [Llama 2](https://huggingface.co/meta-llama) | 7B/13B/70B | llama2 |
| [Llama 3-3.2](https://huggingface.co/meta-llama) | 1B/3B/8B/70B | llama3 |
| [LLaVA-1.5](https://huggingface.co/llava-hf) | 7B/13B | llava |
| [LLaVA-NeXT](https://huggingface.co/llava-hf) | 7B/8B/13B/34B/72B/110B | llava_next |
| [LLaVA-NeXT-Video](https://huggingface.co/llava-hf) | 7B/34B | llava_next_video |
| [MiniCPM](https://huggingface.co/openbmb) | 1B/2B/4B | cpm/cpm3 |
| [Mistral/Mixtral](https://huggingface.co/mistralai) | 7B/8x7B/8x22B | mistral |
| [OLMo](https://huggingface.co/allenai) | 1B/7B | - |
| [PaliGemma](https://huggingface.co/google) | 3B | paligemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - |
| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi |
| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen |
| [Qwen2-VL](https://huggingface.co/Qwen) | 2B/7B/72B | qwen2_vl |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |
| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse |
| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai) | 1.5B/6B/9B/34B | yi |
| [Yi-VL](https://huggingface.co/01-ai) | 6B/34B | yi_vl |
| [Yuan 2](https://huggingface.co/IEITYuan) | 2B/51B/102B | yuan |
> [!NOTE]
> 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
......@@ -271,6 +283,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- [Magpie-Pro-300K-Filtered (en)](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-300K-Filtered)
- [Magpie-ultra-v0.1 (en)](https://huggingface.co/datasets/argilla/magpie-ultra-v0.1)
- [LLaVA mixed (en&zh)](https://huggingface.co/datasets/BUAADreamer/llava-en-zh-300k)
- [Pokemon-gpt4o-captions (en&zh)](https://huggingface.co/datasets/jugg1024/pokemon-gpt4o-captions)
- [Open Assistant (de)](https://huggingface.co/datasets/mayflowergmbh/oasst_de)
- [Dolly 15k (de)](https://huggingface.co/datasets/mayflowergmbh/dolly-15k_de)
- [Alpaca GPT4 (de)](https://huggingface.co/datasets/mayflowergmbh/alpaca-gpt4_de)
......@@ -287,6 +300,8 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
- [DPO mixed (en&zh)](https://huggingface.co/datasets/hiyouga/DPO-En-Zh-20k)
- [UltraFeedback (en)](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized)
- [RLHF-V (en)](https://huggingface.co/datasets/openbmb/RLHF-V-Dataset)
- [VLFeedback (en)](https://huggingface.co/datasets/Zhihui/VLFeedback)
- [Orca DPO Pairs (en)](https://huggingface.co/datasets/Intel/orca_dpo_pairs)
- [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf)
- [Nectar (en)](https://huggingface.co/datasets/berkeley-nest/Nectar)
......@@ -349,7 +364,7 @@ cd LLaMA-Factory
pip install -e ".[torch,metrics]"
```
可选的额外依赖项：torch、torch-npu、metrics、deepspeed、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality
可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、galore、badam、adam-mini、qwen、modelscope、quality
> [!TIP]
> 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。
......
assets/wechat.jpg
View replaced file @ 731cf9b8 View file @ 27a7ad86
assets/wechat.jpg

122 KB | W: | H:

assets/wechat.jpg

199 KB | W: | H:

assets/wechat.jpg
assets/wechat.jpg
assets/wechat.jpg
assets/wechat.jpg
  • 2-up
  • Swipe
  • Onion skin
assets/wechat_npu.jpg
View replaced file @ 731cf9b8 View file @ 27a7ad86
assets/wechat_npu.jpg

193 KB | W: | H:

assets/wechat_npu.jpg

168 KB | W: | H:

assets/wechat_npu.jpg
assets/wechat_npu.jpg
assets/wechat_npu.jpg
assets/wechat_npu.jpg
  • 2-up
  • Swipe
  • Onion skin
data/README.md
View file @ 27a7ad86
......@@ -23,6 +23,7 @@ Currently we support datasets in **alpaca** and **sharegpt** format.
"system": "the column name in the dataset containing the system prompts. (default: None)",
"tools": "the column name in the dataset containing the tool description. (default: None)",
"images": "the column name in the dataset containing the image inputs. (default: None)",
"videos": "the column name in the dataset containing the videos inputs. (default: None)",
"chosen": "the column name in the dataset containing the chosen answers. (default: None)",
"rejected": "the column name in the dataset containing the rejected answers. (default: None)",
"kto_tag": "the column name in the dataset containing the kto tags. (default: None)"
......@@ -107,7 +108,7 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
### Preference Dataset
Preference datasets are used for reward modeling, DPO training and ORPO training.
Preference datasets are used for reward modeling, DPO training, ORPO and SimPO training.
It requires a better response in `chosen` column and a worse response in `rejected` column.
......@@ -139,67 +140,15 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
### KTO Dataset
- [Example dataset](kto_en_demo.json)
KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
```json
[
{
"instruction": "human instruction (required)",
"input": "human input (optional)",
"output": "model response (required)",
"kto_tag": "human feedback [true/false] (required)"
}
]
```
Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
```json
"dataset_name": {
"file_name": "data.json",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"kto_tag": "kto_tag"
}
}
```
### Multimodal Dataset
An additional column `kto_tag` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
- [Example dataset](mllm_demo.json)
### Multimodal Image Dataset
Multimodal datasets require a `images` column containing the paths to the input images. Currently we only support one image.
```json
[
{
"instruction": "human instruction (required)",
"input": "human input (optional)",
"output": "model response (required)",
"images": [
"image path (required)"
]
}
]
```
An additional column `images` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
### Multimodal Video Dataset
```json
"dataset_name": {
"file_name": "data.json",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"images": "images"
}
}
```
An additional column `videos` is required. Please refer to the [sharegpt](#sharegpt-format) format for details.
## Sharegpt Format
......@@ -252,6 +201,10 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
}
```
### Pre-training Dataset
Not yet supported, please use the [alpaca](#alpaca-format) format.
### Preference Dataset
- [Example dataset](dpo_en_demo.json)
......@@ -302,6 +255,125 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
}
```
### KTO Dataset
- [Example dataset](kto_en_demo.json)
KTO datasets require a extra `kto_tag` column containing the boolean human feedback.
```json
[
{
"conversations": [
{
"from": "human",
"value": "human instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"kto_tag": "human feedback [true/false] (required)"
}
]
```
Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
```json
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"kto_tag": "kto_tag"
}
}
```
### Multimodal Image Dataset
- [Example dataset](mllm_demo.json)
Multimodal image datasets require a `images` column containing the paths to the input images.
The number of images should be identical to the `<image>` tokens in the conversations.
```json
[
{
"conversations": [
{
"from": "human",
"value": "<image>human instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"images": [
"image path (required)"
]
}
]
```
Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
```json
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"images": "images"
}
}
```
### Multimodal Video Dataset
- [Example dataset](mllm_video_demo.json)
Multimodal video datasets require a `videos` column containing the paths to the input videos.
The number of videos should be identical to the `<video>` tokens in the conversations.
```json
[
{
"conversations": [
{
"from": "human",
"value": "<video>human instruction"
},
{
"from": "gpt",
"value": "model response"
}
],
"videos": [
"video path (required)"
]
}
]
```
Regarding the above dataset, the *dataset description* in `dataset_info.json` should be:
```json
"dataset_name": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"videos": "videos"
}
}
```
### OpenAI Format
The openai format is simply a special case of the sharegpt format, where the first message may be a system prompt.
......@@ -345,7 +417,3 @@ Regarding the above dataset, the *dataset description* in `dataset_info.json` sh
}
}
```
The KTO datasets and multimodal datasets in sharegpt format are similar to the alpaca format.
Pre-training datasets are **incompatible** with the sharegpt format.
data/README_zh.md
View file @ 27a7ad86
......@@ -23,6 +23,7 @@
"system": "数据集代表系统提示的表头名称（默认：None）",
"tools": "数据集代表工具描述的表头名称（默认：None）",
"images": "数据集代表图像输入的表头名称（默认：None）",
"videos": "数据集代表视频输入的表头名称（默认：None）",
"chosen": "数据集代表更优回答的表头名称（默认：None）",
"rejected": "数据集代表更差回答的表头名称（默认：None）",
"kto_tag": "数据集代表 KTO 标签的表头名称（默认：None）"
......@@ -107,7 +108,7 @@
### 偏好数据集
偏好数据集用于奖励模型训练、DPO 训练和 ORPO 训练。
偏好数据集用于奖励模型训练、DPO 训练、ORPO 训练和 SimPO 训练。
它需要在 `chosen` 列中提供更优的回答，并在 `rejected` 列中提供更差的回答。
......@@ -139,67 +140,15 @@
### KTO 数据集
- [样例数据集](kto_en_demo.json)
KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人类反馈。
```json
[
{
"instruction": "人类指令（必填）",
"input": "人类输入（选填）",
"output": "模型回答（必填）",
"kto_tag": "人类反馈 [true/false]（必填）"
}
]
```
对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
```json
"数据集名称": {
"file_name": "data.json",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"kto_tag": "kto_tag"
}
}
```
### 多模态数据集
KTO 数据集需要提供额外的 `kto_tag` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
- [样例数据集](mllm_demo.json)
### 多模态图像数据集
多模态数据集需要额外添加一个 `images` 列，包含输入图像的路径。目前我们仅支持单张图像输入。
```json
[
{
"instruction": "人类指令（必填）",
"input": "人类输入（选填）",
"output": "模型回答（必填）",
"images": [
"图像路径（必填）"
]
}
]
```
多模态图像数据集需要提供额外的 `images` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
### 多模态视频数据集
```json
"数据集名称": {
"file_name": "data.json",
"columns": {
"prompt": "instruction",
"query": "input",
"response": "output",
"images": "images"
}
}
```
多模态视频数据集需要提供额外的 `videos` 列。详情请参阅 [sharegpt](#sharegpt-格式)。
## Sharegpt 格式
......@@ -252,6 +201,10 @@ KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人
}
```
### 预训练数据集
尚不支持，请使用 [alpaca](#alpaca-格式) 格式。
### 偏好数据集
- [样例数据集](dpo_zh_demo.json)
......@@ -302,6 +255,125 @@ Sharegpt 格式的偏好数据集同样需要在 `chosen` 列中提供更优的
}
```
### KTO 数据集
- [样例数据集](kto_en_demo.json)
KTO 数据集需要额外添加一个 `kto_tag` 列，包含 bool 类型的人类反馈。
```json
[
{
"conversations": [
{
"from": "human",
"value": "人类指令"
},
{
"from": "gpt",
"value": "模型回答"
}
],
"kto_tag": "人类反馈 [true/false]（必填）"
}
]
```
对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
```json
"数据集名称": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"kto_tag": "kto_tag"
}
}
```
### 多模态图像数据集
- [样例数据集](mllm_demo.json)
多模态图像数据集需要额外添加一个 `images` 列，包含输入图像的路径。
注意图片的数量必须与文本中所有 `<image>` 标记的数量严格一致。
```json
[
{
"conversations": [
{
"from": "human",
"value": "<image>人类指令"
},
{
"from": "gpt",
"value": "模型回答"
}
],
"images": [
"图像路径（必填）"
]
}
]
```
对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
```json
"数据集名称": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"images": "images"
}
}
```
### 多模态视频数据集
- [样例数据集](mllm_video_demo.json)
多模态视频数据集需要额外添加一个 `videos` 列，包含输入视频的路径。
注意视频的数量必须与文本中所有 `<video>` 标记的数量严格一致。
```json
[
{
"conversations": [
{
"from": "human",
"value": "<video>人类指令"
},
{
"from": "gpt",
"value": "模型回答"
}
],
"videos": [
"视频路径（必填）"
]
}
]
```
对于上述格式的数据，`dataset_info.json` 中的*数据集描述*应为：
```json
"数据集名称": {
"file_name": "data.json",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"videos": "videos"
}
}
```
### OpenAI 格式
OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消息可能是系统提示词。
......@@ -345,7 +417,3 @@ OpenAI 格式仅仅是 sharegpt 格式的一种特殊情况，其中第一条消
}
}
```
Sharegpt 格式中的 KTO 数据集和多模态数据集与 alpaca 格式的类似。
预训练数据集**不支持** sharegpt 格式。
data/dataset_info.json
View file @ 27a7ad86
......@@ -38,6 +38,20 @@
"assistant_tag": "assistant"
}
},
"mllm_video_demo": {
"file_name": "mllm_video_demo.json",
"formatting": "sharegpt",
"columns": {
"messages": "messages",
"videos": "videos"
},
"tags": {
"role_tag": "role",
"content_tag": "content",
"user_tag": "user",
"assistant_tag": "assistant"
}
},
"alpaca_en": {
"hf_hub_url": "llamafactory/alpaca_en",
"ms_hub_url": "llamafactory/alpaca_en"
......@@ -340,6 +354,14 @@
"assistant_tag": "assistant"
}
},
"pokemon_cap": {
"hf_hub_url": "llamafactory/pokemon-gpt4o-captions",
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"images": "images"
}
},
"mllm_pt_demo": {
"hf_hub_url": "BUAADreamer/mllm_pt_demo",
"formatting": "sharegpt",
......@@ -433,6 +455,28 @@
"rejected": "rejected"
}
},
"rlhf_v": {
"hf_hub_url": "llamafactory/RLHF-V",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected",
"images": "images"
}
},
"vlfeedback": {
"hf_hub_url": "Zhihui/VLFeedback",
"ranking": true,
"formatting": "sharegpt",
"columns": {
"messages": "conversations",
"chosen": "chosen",
"rejected": "rejected",
"images": "images"
}
},
"orca_pairs": {
"hf_hub_url": "Intel/orca_dpo_pairs",
"ranking": true,
......
data/mllm_demo.json
View file @ 27a7ad86
......@@ -2,7 +2,7 @@
{
"messages": [
{
"content": "Who are they?",
"content": "<image>Who are they?",
"role": "user"
},
{
......@@ -25,7 +25,7 @@
{
"messages": [
{
"content": "Who is he?",
"content": "<image>Who is he?",
"role": "user"
},
{
......@@ -48,7 +48,7 @@
{
"messages": [
{
"content": "Please describe this image",
"content": "<image>Please describe this image",
"role": "user"
},
{
......@@ -71,7 +71,7 @@
{
"messages": [
{
"content": "他们是谁？",
"content": "<image>他们是谁？",
"role": "user"
},
{
......@@ -94,7 +94,7 @@
{
"messages": [
{
"content": "他是谁？",
"content": "<image>他是谁？",
"role": "user"
},
{
......@@ -117,7 +117,7 @@
{
"messages": [
{
"content": "请描述这张图片",
"content": "<image>请描述这张图片",
"role": "user"
},
{
......
data/mllm_video_demo.json 0 → 100644
View file @ 27a7ad86
[
{
"messages": [
{
"content": "<video>Why is this video funny?",
"role": "user"
},
{
"content": "Because a baby is reading, and he is so cute!",
"role": "assistant"
}
],
"videos": [
"mllm_demo_data/1.mp4"
]
},
{
"messages": [
{
"content": "<video>What is she doing?",
"role": "user"
},
{
"content": "She is cooking.",
"role": "assistant"
}
],
"videos": [
"mllm_demo_data/2.avi"
]
},
{
"messages": [
{
"content": "<video>What's in the video?",
"role": "user"
},
{
"content": "A baby is playing in the living room.",
"role": "assistant"
}
],
"videos": [
"mllm_demo_data/3.mp4"
]
}
]
\ No newline at end of file
docker/docker-cuda/Dockerfile 0 → 100644
View file @ 27a7ad86
# Use the NVIDIA official image with PyTorch 2.3.0
# https://docs.nvidia.com/deeplearning/frameworks/pytorch-release-notes/rel-24-02.html
FROM nvcr.io/nvidia/pytorch:24.02-py3
# Define environments
ENV MAX_JOBS=4
ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
# Define installation arguments
ARG INSTALL_BNB=false
ARG INSTALL_VLLM=false
ARG INSTALL_DEEPSPEED=false
ARG INSTALL_FLASHATTN=false
ARG INSTALL_LIGER_KERNEL=false
ARG INSTALL_HQQ=false
ARG INSTALL_EETQ=false
ARG PIP_INDEX=https://pypi.org/simple
# Set the working directory
WORKDIR /app
# Install the requirements
COPY requirements.txt /app
RUN pip config set global.index-url "$PIP_INDEX" && \
pip config set global.extra-index-url "$PIP_INDEX" && \
python -m pip install --upgrade pip && \
python -m pip install -r requirements.txt
# Copy the rest of the application into the image
COPY . /app
# Install the LLaMA Factory
RUN EXTRA_PACKAGES="metrics"; \
if [ "$INSTALL_BNB" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
fi; \
if [ "$INSTALL_VLLM" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
fi; \
if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
fi; \
if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
fi; \
if [ "$INSTALL_HQQ" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
fi; \
if [ "$INSTALL_EETQ" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},eetq"; \
fi; \
pip install -e ".[$EXTRA_PACKAGES]"
# Rebuild flash attention
RUN pip uninstall -y transformer-engine flash-attn && \
if [ "$INSTALL_FLASHATTN" == "true" ]; then \
pip uninstall -y ninja && pip install ninja && \
pip install --no-cache-dir flash-attn --no-build-isolation; \
fi
# Set up volumes
VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
# Expose port 7860 for the LLaMA Board
ENV GRADIO_SERVER_PORT 7860
EXPOSE 7860
# Expose port 8000 for the API service
ENV API_PORT 8000
EXPOSE 8000
docker/docker-cuda/docker-compose.yml 0 → 100644
View file @ 27a7ad86
services:
llamafactory:
build:
dockerfile: ./docker/docker-cuda/Dockerfile
context: ../..
args:
INSTALL_BNB: false
INSTALL_VLLM: false
INSTALL_DEEPSPEED: false
INSTALL_FLASHATTN: false
INSTALL_LIGER_KERNEL: false
INSTALL_HQQ: false
INSTALL_EETQ: false
PIP_INDEX: https://pypi.org/simple
container_name: llamafactory
volumes:
- ../../hf_cache:/root/.cache/huggingface
- ../../ms_cache:/root/.cache/modelscope
- ../../data:/app/data
- ../../output:/app/output
ports:
- "7860:7860"
- "8000:8000"
ipc: host
tty: true
stdin_open: true
command: bash
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: "all"
capabilities: [gpu]
restart: unless-stopped
docker/docker-npu/Dockerfile 0 → 100644
View file @ 27a7ad86
# Use the Ubuntu 22.04 image with CANN 8.0.rc1
# More versions can be found at https://hub.docker.com/r/ascendai/cann/tags
# FROM ascendai/cann:8.0.rc1-910-ubuntu22.04-py3.8
FROM ascendai/cann:8.0.rc1-910b-ubuntu22.04-py3.8
# FROM ascendai/cann:8.0.rc1-910-openeuler22.03-py3.8
# FROM ascendai/cann:8.0.rc1-910b-openeuler22.03-py3.8
# Define environments
ENV DEBIAN_FRONTEND=noninteractive
# Define installation arguments
ARG INSTALL_DEEPSPEED=false
ARG PIP_INDEX=https://pypi.org/simple
ARG TORCH_INDEX=https://download.pytorch.org/whl/cpu
# Set the working directory
WORKDIR /app
# Install the requirements
COPY requirements.txt /app
RUN pip config set global.index-url "$PIP_INDEX" && \
pip config set global.extra-index-url "$TORCH_INDEX" && \
python -m pip install --upgrade pip && \
python -m pip install -r requirements.txt
# Copy the rest of the application into the image
COPY . /app
# Install the LLaMA Factory
RUN EXTRA_PACKAGES="torch-npu,metrics"; \
if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
fi; \
pip install -e ".[$EXTRA_PACKAGES]"
# Set up volumes
VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
# Expose port 7860 for the LLaMA Board
ENV GRADIO_SERVER_PORT 7860
EXPOSE 7860
# Expose port 8000 for the API service
ENV API_PORT 8000
EXPOSE 8000
docker/docker-npu/docker-compose.yml 0 → 100644
View file @ 27a7ad86
services:
llamafactory:
build:
dockerfile: ./docker/docker-npu/Dockerfile
context: ../..
args:
INSTALL_DEEPSPEED: false
PIP_INDEX: https://pypi.org/simple
container_name: llamafactory
volumes:
- ../../hf_cache:/root/.cache/huggingface
- ../../ms_cache:/root/.cache/modelscope
- ../../data:/app/data
- ../../output:/app/output
- /usr/local/dcmi:/usr/local/dcmi
- /usr/local/bin/npu-smi:/usr/local/bin/npu-smi
- /usr/local/Ascend/driver:/usr/local/Ascend/driver
- /etc/ascend_install.info:/etc/ascend_install.info
ports:
- "7860:7860"
- "8000:8000"
ipc: host
tty: true
stdin_open: true
command: bash
devices:
- /dev/davinci0
- /dev/davinci_manager
- /dev/devmm_svm
- /dev/hisi_hdc
restart: unless-stopped
docker/docker-rocm/Dockerfile 0 → 100644
View file @ 27a7ad86
FROM hardandheavy/transformers-rocm:2.2.0
# Define environments
ENV MAX_JOBS=4
ENV FLASH_ATTENTION_FORCE_BUILD=TRUE
ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
# Define installation arguments
ARG INSTALL_BNB=false
ARG INSTALL_VLLM=false
ARG INSTALL_DEEPSPEED=false
ARG INSTALL_FLASHATTN=false
ARG INSTALL_LIGER_KERNEL=false
ARG INSTALL_HQQ=false
ARG PIP_INDEX=https://pypi.org/simple
# Set the working directory
WORKDIR /app
# Install the requirements
COPY requirements.txt /app
RUN pip config set global.index-url "$PIP_INDEX" && \
pip config set global.extra-index-url "$PIP_INDEX" && \
python -m pip install --upgrade pip && \
python -m pip install -r requirements.txt
# Copy the rest of the application into the image
COPY . /app
# Install the LLaMA Factory
RUN EXTRA_PACKAGES="metrics"; \
if [ "$INSTALL_BNB" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},bitsandbytes"; \
fi; \
if [ "$INSTALL_VLLM" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},vllm"; \
fi; \
if [ "$INSTALL_DEEPSPEED" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},deepspeed"; \
fi; \
if [ "$INSTALL_LIGER_KERNEL" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},liger-kernel"; \
fi; \
if [ "$INSTALL_HQQ" == "true" ]; then \
EXTRA_PACKAGES="${EXTRA_PACKAGES},hqq"; \
fi; \
pip install -e ".[$EXTRA_PACKAGES]"
# Rebuild flash attention
RUN pip uninstall -y transformer-engine flash-attn && \
if [ "$INSTALL_FLASHATTN" == "true" ]; then \
pip uninstall -y ninja && pip install ninja && \
pip install --no-cache-dir flash-attn --no-build-isolation; \
fi
# Set up volumes
VOLUME [ "/root/.cache/huggingface", "/root/.cache/modelscope", "/app/data", "/app/output" ]
# Expose port 7860 for the LLaMA Board
ENV GRADIO_SERVER_PORT 7860
EXPOSE 7860
# Expose port 8000 for the API service
ENV API_PORT 8000
EXPOSE 8000
docker/docker-rocm/docker-compose.yml 0 → 100644
View file @ 27a7ad86
services:
llamafactory:
build:
dockerfile: ./docker/docker-rocm/Dockerfile
context: ../..
args:
INSTALL_BNB: false
INSTALL_VLLM: false
INSTALL_DEEPSPEED: false
INSTALL_FLASHATTN: false
INSTALL_LIGER_KERNEL: false
INSTALL_HQQ: false
PIP_INDEX: https://pypi.org/simple
container_name: llamafactory
volumes:
- ../../hf_cache:/root/.cache/huggingface
- ../../ms_cache:/root/.cache/modelscope
- ../../data:/app/data
- ../../output:/app/output
- ../../saves:/app/saves
ports:
- "7860:7860"
- "8000:8000"
ipc: host
tty: true
stdin_open: true
command: bash
devices:
- /dev/kfd:/dev/kfd
- /dev/dri:/dev/dri
restart: unless-stopped
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment