Coati - ColossalAI Talking Intelligence
## Table of Contents
- [Table of Contents](#table-of-contents)
- [What is Coati ?](#what-is-coati-)
- [Online demo](#online-demo)
- [Install](#install)
- [Install the environment](#install-the-environment)
- [Install the Transformers](#install-the-transformers)
- [How to use?](#how-to-use)
- [Supervised datasets collection](#supervised-datasets-collection)
- [Stage1 - Supervised instructs tuning](#stage1---supervised-instructs-tuning)
- [Stage2 - Training reward model](#stage2---training-reward-model)
- [Stage3 - Training model with reinforcement learning by human feedback](#stage3---training-model-with-reinforcement-learning-by-human-feedback)
- [Inference - After Training](#inference---after-training)
- [Coati7B examples](#coati7b-examples)
- [Generation](#generation)
- [Open QA](#open-qa)
- [Limitation for LLaMA-finetuned models](#limitation-for-llama-finetuned-models)
- [Limitation of dataset](#limitation-of-dataset)
- [FAQ](#faq)
- [How to save/load checkpoint](#how-to-saveload-checkpoint)
- [The Plan](#the-plan)
- [Real-time progress](#real-time-progress)
- [Invitation to open-source contribution](#invitation-to-open-source-contribution)
- [Quick Preview](#quick-preview)
- [Authors](#authors)
- [Citations](#citations)
- [Licenses](#licenses)
---
## What is Coati ?
Coati is a large language model developed by Colossal-AI, which is also a unified large language model framework that has implemented the following functions
- Supports comprehensive large-model training acceleration capabilities for ColossalAI, without requiring knowledge of complex distributed training algorithms
- Supervised datasets collection
- Supervised insturcts fine-tuning
- Training reward model
- Reinforcement learning with human feedback
- Quantization inference
- Fast model deploying
- Perfectly integration with the Hugging Face ecosystem, high degree of model customization
More details can be found in the [blog](https://www.hpc-ai.tech/blog/colossal-ai-chatgpt).
## Online demo
You can experience the performance of Coati7B on this page.
[chat.colossalai.org](https://chat.colossalai.org/)
> Warning: Due to model and dataset size limitations, Coati is just a baby model, Coati7B may output incorrect information and lack the ability for multi-turn dialogue. There is still significant room for improvement.
## Install
### Install the environment
```shell
conda create -n coati
conda activate coati
pip install .
```
### Install the Transformers
Given Hugging Face hasn't officially supported the LLaMA models, We fork a branch of Transformers that can be compatible with our code
```shell
git clone https://github.com/hpcaitech/transformers
cd transformers
pip install .
```
## How to use?
### Supervised datasets collection
we colllected 104K bilingual dataset of Chinese and English, and you can find the datasets in this repo
[InstructionWild](https://github.com/XueFuzhao/InstructionWild)
Here is how we collected the data
### Stage1 - Supervised instructs tuning
Stage1 is supervised instructs fine-tuning, which uses the datasets mentioned earlier to fine-tune the model
you can run the `examples/train_sft.sh` to start a supervised instructs fine-tuning
```
torchrun --standalone --nproc_per_node=4 train_sft.py \
--pretrain "/path/to/LLaMa-7B/" \
--model 'llama' \
--strategy colossalai_zero2 \
--log_interval 10 \
--save_path /path/to/Coati-7B \
--dataset /path/to/data.json \
--batch_size 4 \
--accimulation_steps 8 \
--lr 2e-5 \
--max_datasets_size 512 \
--max_epochs 1 \
```
### Stage2 - Training reward model
Stage2 trains a reward model, which obtains corresponding scores by manually ranking different outputs for the same prompt and supervises the training of the reward model
you can run the `examples/train_rm.sh` to start a reward model training
```
torchrun --standalone --nproc_per_node=4 train_reward_model.py
--pretrain "/path/to/LLaMa-7B/" \
--model 'llama' \
--strategy colossalai_zero2 \
--loss_fn 'log_exp'\
--save_path 'rmstatic.pt' \
```
### Stage3 - Training model with reinforcement learning by human feedback
Stage3 uses reinforcement learning algorithm, which is the most complex part of the training process:
you can run the `examples/train_prompts.sh` to start training PPO with human feedback
```
torchrun --standalone --nproc_per_node=4 train_prompts.py \
--pretrain "/path/to/LLaMa-7B/" \
--model 'llama' \
--strategy colossalai_zero2 \
--prompt_path /path/to/your/prompt_dataset \
--pretrain_dataset /path/to/your/pretrain_dataset \
--rm_pretrain /your/pretrain/rm/defination \
--rm_path /your/rm/model/path
```
For more details, see [`examples/`](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Chat/examples).
### Inference - After Training
#### 8-bit setup
8-bit quantization is originally supported by the latest [transformers](https://github.com/huggingface/transformers). Please install it from source.
Please ensure you have downloaded HF-format model weights of LLaMA models.
Usage:
```python
from transformers import LlamaForCausalLM
USE_8BIT = True # use 8-bit quantization; otherwise, use fp16
model = LlamaForCausalLM.from_pretrained(
"pretrained/path",
load_in_8bit=USE_8BIT,
torch_dtype=torch.float16,
device_map="auto",
)
if not USE_8BIT:
model.half() # use fp16
model.eval()
```
**Troubleshooting**: if you get error indicating your CUDA-related libraries not found when loading 8-bit model, you can check whether your `LD_LIBRARY_PATH` is correct.
E.g. you can set `export LD_LIBRARY_PATH=$CUDA_HOME/lib64:$LD_LIBRARY_PATH`.
#### 4-bit setup
Please ensure you have downloaded HF-format model weights of LLaMA models first.
Then you can follow [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa). This lib provides efficient CUDA kernels and weight convertion script.
After installing this lib, we may convert the original HF-format LLaMA model weights to 4-bit version.
```shell
CUDA_VISIBLE_DEVICES=0 python llama.py /path/to/pretrained/llama-7b c4 --wbits 4 --groupsize 128 --save llama7b-4bit.pt
```
Run this command in your cloned `GPTQ-for-LLaMa` directory, then you will get a 4-bit weight file `llama7b-4bit-128g.pt`.
**Troubleshooting**: if you get error about `position_ids`, you can checkout to commit `50287c3b9ae4a3b66f6b5127c643ec39b769b155`(`GPTQ-for-LLaMa` repo).
For more details, see [`inference/`](https://github.com/hpcaitech/ColossalAI/tree/main/applications/Chat/inference).
## Coati7B examples
### Generation
E-mail
coding
regex
Tex
writing
Table
Game
Travel
Physical
Chemical
Economy
- Up to 7.73 times faster for single server training and 1.42 times faster for single-GPU inference
- Up to 10.3x growth in model capacity on one GPU
- A mini demo training process requires only 1.62GB of GPU memory (any consumer-grade GPU)
- Increase the capacity of the fine-tuning model by up to 3.7 times on a single GPU
- Keep in a sufficiently high running speed
## Authors
Coati is developed by ColossalAI Team: [Fazzie](https://fazzie-key.cool/about/index.html), [FrankLeeeee](https://github.com/FrankLeeeee), [BlueRum](https://github.com/ht-zhou), [ver217](https://github.com/ver217)
The Phd student [Zangwei Zheng](https://github.com/zhengzangw) and [Xue Fuzhao](https://github.com/XueFuzhao) also contributed a lot to this project.
## Citations
```bibtex
@article{Hu2021LoRALA,
title = {LoRA: Low-Rank Adaptation of Large Language Models},
author = {Edward J. Hu and Yelong Shen and Phillip Wallis and Zeyuan Allen-Zhu and Yuanzhi Li and Shean Wang and Weizhu Chen},
journal = {ArXiv},
year = {2021},
volume = {abs/2106.09685}
}
@article{ouyang2022training,
title={Training language models to follow instructions with human feedback},
author={Ouyang, Long and Wu, Jeff and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll L and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},
journal={arXiv preprint arXiv:2203.02155},
year={2022}
}
@article{touvron2023llama,
title={LLaMA: Open and Efficient Foundation Language Models},
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
journal={arXiv preprint arXiv:2302.13971},
year={2023}
}
@misc{alpaca,
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
title = {Stanford Alpaca: An Instruction-following LLaMA model},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
}
@misc{instructionwild,
author = {Fuzhao Xue and Zangwei Zheng and Yang You },
title = {Instruction in the Wild: A User-based Instruction Dataset},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/XueFuzhao/InstructionWild}},
}
```
## Licenses
Coati is licensed under the [Apache 2.0 License](LICENSE).