Skip to content

GitLab

"applications/Chat/coati/vscode:/vscode.git/clone" did not exist on "773955abfaa3b5aef832ad4a33ce053183edee0e"
Unverified Commit d512a4d3 authored by binmakeswell's avatar binmakeswell Committed by GitHub
Browse files

[doc] add llama2 domain-specific solution news (#4789) 

* [doc] add llama2 domain-specific solution news
parent ce777853
Show whitespace changes
Inline Side-by-side
Showing with 79 additions and 7 deletions
README.md
View file @ d512a4d3
......@@ -25,6 +25,7 @@
</div>
## Latest News
* [2023/09] [One Half-Day of Training Using a Few Hundred Dollars Yields Similar Results to Mainstream Large Models, Open-Source and Commercial-Free Domain-Specific Llm Solution](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
* [2023/09] [70 Billion Parameter LLaMA2 Model Training Accelerated by 195%](https://www.hpc-ai.tech/blog/70b-llama2-training)
* [2023/07] [HPC-AI Tech Raises 22 Million USD in Series A Funding](https://www.hpc-ai.tech/blog/hpc-ai-tech-raises-22-million-usd-in-series-a-funding-to-fuel-team-expansion-and-business-growth)
* [2023/07] [65B Model Pretraining Accelerated by 38%, Best Practices for Building LLaMA-Like Base Models Open-Source](https://www.hpc-ai.tech/blog/large-model-pretraining)
......@@ -33,8 +34,6 @@
* [2023/03] [AWS and Google Fund Colossal-AI with Startup Cloud Programs](https://www.hpc-ai.tech/blog/aws-and-google-fund-colossal-ai-with-startup-cloud-programs)
* [2023/02] [Open Source Solution Replicates ChatGPT Training Process! Ready to go with only 1.6GB GPU Memory](https://www.hpc-ai.tech/blog/colossal-ai-chatgpt)
* [2023/01] [Hardware Savings Up to 46 Times for AIGC and Automatic Parallelism](https://medium.com/pytorch/latest-colossal-ai-boasts-novel-automatic-parallelism-and-offers-savings-up-to-46x-for-stable-1453b48f3f02)
* [2022/11] [Diffusion Pretraining and Hardware Fine-Tuning Can Be Almost 7X Cheaper](https://www.hpc-ai.tech/blog/diffusion-pretraining-and-hardware-fine-tuning-can-be-almost-7x-cheaper)
* [2022/10] [Use a Laptop to Analyze 90% of Proteins, With a Single-GPU Inference Sequence Exceeding 10,000](https://www.hpc-ai.tech/blog/use-a-laptop-to-analyze-90-of-proteins-with-a-single-gpu-inference-sequence-exceeding)
## Table of Contents
<ul>
......@@ -43,6 +42,7 @@
<li>
<a href="#Colossal-AI-in-the-Real-World">Colossal-AI for Real World Applications</a>
<ul>
<li><a href="#Colossal-LLaMA-2">Colossal-LLaMA-2: One Half-Day of Training Using a Few Hundred Dollars Yields Similar Results to Mainstream Large Models, Open-Source and Commercial-Free Domain-Specific Llm Solution</a></li>
<li><a href="#ColossalChat">ColossalChat: An Open-Source Solution for Cloning ChatGPT With a Complete RLHF Pipeline</a></li>
<li><a href="#AIGC">AIGC: Acceleration of Stable Diffusion</a></li>
<li><a href="#Biomedicine">Biomedicine: Acceleration of AlphaFold Protein Structure</a></li>
......@@ -127,6 +127,36 @@ distributed training and inference in a few lines.
## Colossal-AI in the Real World
### Colossal-LLaMA-2
- One half-day of training using a few hundred dollars yields similar results to mainstream large models, open-source and commercial-free domain-specific LLM solution.
[[code]](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Colossal-LLaMA-2)
[[blog]](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
[[model weights]](https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-7b-base)
| | Backbone | Tokens Consumed | | MMLU | CMMLU | AGIEval | GAOKAO | CEval |
| :----------------------------: | :--------: | :-------------: | :------------------: | :-----------: | :-----: | :----: | :----: | :------------------------------: |
| | | - | | 5-shot | 5-shot | 5-shot | 0-shot | 5-shot |
| Baichuan-7B | - | 1.2T | | 42.32 (42.30) | 44.53 (44.02) | 38.72 | 36.74 | 42.80 |
| Baichuan-13B-Base | - | 1.4T | | 50.51 (51.60) | 55.73 (55.30) | 47.20 | 51.41 | 53.60 |
| Baichuan2-7B-Base | - | 2.6T | | 46.97 (54.16) | 57.67 (57.07) | 45.76 | 52.60 | 54.00 |
| Baichuan2-13B-Base | - | 2.6T | | 54.84 (59.17) | 62.62 (61.97) | 52.08 | 58.25 | 58.10 |
| ChatGLM-6B | - | 1.0T | | 39.67 (40.63) | 41.17 (-) | 40.10 | 36.53 | 38.90 |
| ChatGLM2-6B | - | 1.4T | | 44.74 (45.46) | 49.40 (-) | 46.36 | 45.49 | 51.70 |
| InternLM-7B | - | 1.6T | | 46.70 (51.00) | 52.00 (-) | 44.77 | 61.64 | 52.80 |
| Qwen-7B | - | 2.2T | | 54.29 (56.70) | 56.03 (58.80) | 52.47 | 56.42 | 59.60 |
| | | | | | | | | |
| Llama-2-7B | - | 2.0T | | 44.47 (45.30) | 32.97 (-) | 32.60 | 25.46 | - |
| Linly-AI/Chinese-LLaMA-2-7B-hf | Llama-2-7B | 1.0T | | 37.43 | 29.92 | 32.00 | 27.57 | - |
| wenge-research/yayi-7b-llama2 | Llama-2-7B | - | | 38.56 | 31.52 | 30.99 | 25.95 | - |
| ziqingyang/chinese-llama-2-7b | Llama-2-7B | - | | 33.86 | 34.69 | 34.52 | 25.18 | 34.2 |
| TigerResearch/tigerbot-7b-base | Llama-2-7B | 0.3T | | 43.73 | 42.04 | 37.64 | 30.61 | - |
| LinkSoul/Chinese-Llama-2-7b | Llama-2-7B | - | | 48.41 | 38.31 | 38.45 | 27.72 | - |
| FlagAlpha/Atom-7B | Llama-2-7B | 0.1T | | 49.96 | 41.10 | 39.83 | 33.00 | - |
| IDEA-CCNL/Ziya-LLaMA-13B-v1.1 | Llama-13B | 0.11T | | 50.25 | 40.99 | 40.04 | 30.54 | - |
| | | | | | | | | |
| **Colossal-LLaMA-2-7b-base** | Llama-2-7B | **0.0085T** | | 53.06 | 49.89 | 51.48 | 58.82 | 50.2 |
### ColossalChat
<div align="center">
......
applications/Colossal-LLaMA-2/README.md
View file @ d512a4d3
......@@ -18,10 +18,14 @@
- [Data](#data)
- [Tokenizer](#tokenizer)
- [Training Strategy](#training-strategy)
- [Bridging Any Domain-specific Large Models](#bridging-any-domain-specific-large-models)
- [Citations](#citations)
## News
* [2023/09] 🔥 TODO We released **Colossal-LLaMA-2-7B-base** based on LLaMA-2. [Download weights](https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-7b-base).
* [2023/09] [One Half-Day of Training Using a Few Hundred Dollars Yields Similar Results to Mainstream Large Models, Open-Source and Commercial-Free Domain-Specific Llm Solution](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
[[code]](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Colossal-LLaMA-2)
[[blog]](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
[[model weights]](https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-7b-base)
## Colossal-LLaMA-2-7B
The [Colossal-AI](https://github.com/hpcaitech/ColossalAI) team has introduced the open-source model **Colossal-LLaMA-2-7B-base**. This model, a derivation of LLaMA-2, has undergone continual pre-training involving approximately 8.5 billion tokens over a duration of 15 hours with 64 A800 GPUs. At a cost of **less than $1,000**, you can achieve results **similar to those that cost millions of dollars to pretrain from scratch**. It is licensed under the LLaMA-2 license and [Apache 2.0 License](https://github.com/hpcaitech/ColossalAI/blob/main/LICENSE) **without any additional commercial use restrictions**. This solution can also be used to build models of specific domain knowledge or tasks.
......@@ -47,7 +51,7 @@ The generation config for all dataset is greedy search.
| Baichuan2-13B-Base | - | 2.6T | | 54.84 (59.17) | 62.62 (61.97) | 52.08 | 58.25 | 58.10 |
| ChatGLM-6B | - | 1.0T | | 39.67 (40.63) | 41.17 (-) | 40.10 | 36.53 | 38.90 |
| ChatGLM2-6B | - | 1.4T | | 44.74 (45.46) | 49.40 (-) | 46.36 | 45.49 | 51.70 |
| InternLM-7B | - | - | | 46.70 (51.00) | 52.00 (-) | 44.77 | 61.64 | 52.80 |
| InternLM-7B | - | 1.6T | | 46.70 (51.00) | 52.00 (-) | 44.77 | 61.64 | 52.80 |
| Qwen-7B | - | 2.2T | | 54.29 (56.70) | 56.03 (58.80) | 52.47 | 56.42 | 59.60 |
| | | | | | | | | |
| Llama-2-7B | - | 2.0T | | 44.47 (45.30) | 32.97 (-) | 32.60 | 25.46 | - |
......@@ -96,7 +100,7 @@ We also recorded the training logs for the experiment
<img src="https://github.com/hpcaitech/public_assets/blob/main/applications/colossal-llama-2/trainingLossByTokens.jpeg?raw=true" width=600/>
</p>
### Import from Transformers
### Import from Transformers (Inference)
To load Colossal-LLaMA-2-7B-base model using Transformers, use the following code:
```Python
from transformers import AutoModelForCausalLM, AutoTokenizer
......@@ -346,6 +350,13 @@ Our experiments have revealed that the distributions within the training dataset
In an effort to achieve a more balanced distribution and exert control over the dataset's ordering, we have adopted a method where we divide each sub-dataset into discrete bins. These bins are then combined to construct individual data buckets, with one bin contributed by each sub-dataset.
### Bridging Any Domain-specific Large Models
Applying the above process to perform knowledge transfer in any field allows for the cost-effective construction of lightweight domain-specific foundational large models.
<p id="domain_specific-llm" align="center">
<img src="https://github.com/hpcaitech/public_assets/blob/main/applications/colossal-llama-2/domain_specific-llm.jpeg?raw=true" width=800/>
</p>
## Citations
```bibtex
@article{bian2021colossal,
......
docs/README-zh-Hans.md
View file @ d512a4d3
......@@ -24,6 +24,7 @@
</div>
## 新闻
* [2023/09] [One Half-Day of Training Using a Few Hundred Dollars Yields Similar Results to Mainstream Large Models, Open-Source and Commercial-Free Domain-Specific Llm Solution](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
* [2023/09] [70 Billion Parameter LLaMA2 Model Training Accelerated by 195%](https://www.hpc-ai.tech/blog/70b-llama2-training)
* [2023/07] [HPC-AI Tech Raises 22 Million USD in Series A Funding](https://www.hpc-ai.tech/blog/hpc-ai-tech-raises-22-million-usd-in-series-a-funding-to-fuel-team-expansion-and-business-growth)
* [2023/07] [65B Model Pretraining Accelerated by 38%, Best Practices for Building LLaMA-Like Base Models Open-Source](https://www.hpc-ai.tech/blog/large-model-pretraining)
......@@ -32,8 +33,6 @@
* [2023/03] [AWS and Google Fund Colossal-AI with Startup Cloud Programs](https://www.hpc-ai.tech/blog/aws-and-google-fund-colossal-ai-with-startup-cloud-programs)
* [2023/02] [Open Source Solution Replicates ChatGPT Training Process! Ready to go with only 1.6GB GPU Memory](https://www.hpc-ai.tech/blog/colossal-ai-chatgpt)
* [2023/01] [Hardware Savings Up to 46 Times for AIGC and Automatic Parallelism](https://medium.com/pytorch/latest-colossal-ai-boasts-novel-automatic-parallelism-and-offers-savings-up-to-46x-for-stable-1453b48f3f02)
* [2022/11] [Diffusion Pretraining and Hardware Fine-Tuning Can Be Almost 7X Cheaper](https://www.hpc-ai.tech/blog/diffusion-pretraining-and-hardware-fine-tuning-can-be-almost-7x-cheaper)
* [2022/10] [Use a Laptop to Analyze 90% of Proteins, With a Single-GPU Inference Sequence Exceeding 10,000](https://www.hpc-ai.tech/blog/use-a-laptop-to-analyze-90-of-proteins-with-a-single-gpu-inference-sequence-exceeding)
## 目录
<ul>
......@@ -42,6 +41,7 @@
<li>
<a href="#Colossal-AI-in-the-Real-World">Colossal-AI 成功案例</a>
<ul>
<li><a href="#Colossal-LLaMA-2">Colossal-LLaMA-2: 千元预算半天训练，效果媲美主流大模型，开源可商用中文LLaMA-2</a></li>
<li><a href="#ColossalChat">ColossalChat：完整RLHF流程0门槛克隆ChatGPT</a></li>
<li><a href="#AIGC">AIGC: 加速 Stable Diffusion</a></li>
<li><a href="#生物医药">生物医药: 加速AlphaFold蛋白质结构预测</a></li>
......@@ -120,6 +120,37 @@ Colossal-AI 为您提供了一系列并行组件。我们的目标是让您的
<p align="right">(<a href="#top">返回顶端</a>)</p>
## Colossal-AI 成功案例
### Colossal-LLaMA-2
- 千元预算半天训练，效果媲美主流大模型，开源可商用中文LLaMA-2
[[代码]](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Colossal-LLaMA-2)
[[博客]](https://www.hpc-ai.tech/blog/one-half-day-of-training-using-a-few-hundred-dollars-yields-similar-results-to-mainstream-large-models-open-source-and-commercial-free-domain-specific-llm-solution)
[[模型权重]](https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-7b-base)
| | Backbone | Tokens Consumed | | MMLU | CMMLU | AGIEval | GAOKAO | CEval |
| :----------------------------: | :--------: | :-------------: | :------------------: | :-----------: | :-----: | :----: | :----: | :------------------------------: |
| | | - | | 5-shot | 5-shot | 5-shot | 0-shot | 5-shot |
| Baichuan-7B | - | 1.2T | | 42.32 (42.30) | 44.53 (44.02) | 38.72 | 36.74 | 42.80 |
| Baichuan-13B-Base | - | 1.4T | | 50.51 (51.60) | 55.73 (55.30) | 47.20 | 51.41 | 53.60 |
| Baichuan2-7B-Base | - | 2.6T | | 46.97 (54.16) | 57.67 (57.07) | 45.76 | 52.60 | 54.00 |
| Baichuan2-13B-Base | - | 2.6T | | 54.84 (59.17) | 62.62 (61.97) | 52.08 | 58.25 | 58.10 |
| ChatGLM-6B | - | 1.0T | | 39.67 (40.63) | 41.17 (-) | 40.10 | 36.53 | 38.90 |
| ChatGLM2-6B | - | 1.4T | | 44.74 (45.46) | 49.40 (-) | 46.36 | 45.49 | 51.70 |
| InternLM-7B | - | 1.6T | | 46.70 (51.00) | 52.00 (-) | 44.77 | 61.64 | 52.80 |
| Qwen-7B | - | 2.2T | | 54.29 (56.70) | 56.03 (58.80) | 52.47 | 56.42 | 59.60 |
| | | | | | | | | |
| Llama-2-7B | - | 2.0T | | 44.47 (45.30) | 32.97 (-) | 32.60 | 25.46 | - |
| Linly-AI/Chinese-LLaMA-2-7B-hf | Llama-2-7B | 1.0T | | 37.43 | 29.92 | 32.00 | 27.57 | - |
| wenge-research/yayi-7b-llama2 | Llama-2-7B | - | | 38.56 | 31.52 | 30.99 | 25.95 | - |
| ziqingyang/chinese-llama-2-7b | Llama-2-7B | - | | 33.86 | 34.69 | 34.52 | 25.18 | 34.2 |
| TigerResearch/tigerbot-7b-base | Llama-2-7B | 0.3T | | 43.73 | 42.04 | 37.64 | 30.61 | - |
| LinkSoul/Chinese-Llama-2-7b | Llama-2-7B | - | | 48.41 | 38.31 | 38.45 | 27.72 | - |
| FlagAlpha/Atom-7B | Llama-2-7B | 0.1T | | 49.96 | 41.10 | 39.83 | 33.00 | - |
| IDEA-CCNL/Ziya-LLaMA-13B-v1.1 | Llama-13B | 0.11T | | 50.25 | 40.99 | 40.04 | 30.54 | - |
| | | | | | | | | |
| **Colossal-LLaMA-2-7b-base** | Llama-2-7B | **0.0085T** | | 53.06 | 49.89 | 51.48 | 58.82 | 50.2 |
### ColossalChat
<div align="center">
......
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