# LLaMA Efficient Tuning [![GitHub Repo stars](https://img.shields.io/github/stars/hiyouga/LLaMA-Efficient-Tuning?style=social)](https://github.com/hiyouga/LLaMA-Efficient-Tuning/stargazers) [![GitHub Code License](https://img.shields.io/github/license/hiyouga/LLaMA-Efficient-Tuning)](LICENSE) [![GitHub last commit](https://img.shields.io/github/last-commit/hiyouga/LLaMA-Efficient-Tuning)](https://github.com/hiyouga/LLaMA-Efficient-Tuning/commits/main) [![PyPI](https://img.shields.io/pypi/v/llmtuner)](https://pypi.org/project/llmtuner/) [![GitHub pull request](https://img.shields.io/badge/PRs-welcome-blue)](https://github.com/hiyouga/LLaMA-Efficient-Tuning/pulls) 👋 Join our [WeChat](assets/wechat.jpg). \[ English | [中文](README_zh.md) \] ## Changelog [23/08/18] Now we support **resuming training**, upgrade `transformers` to `4.31.0` to enjoy this feature. [23/08/12] Now we support **RoPE scaling** to extend the context length of the LLaMA models. Try `--rope_scaling linear` argument in training and `--rope_scaling dynamic` argument at inference to extrapolate the position embeddings. [23/08/11] Now we support **[DPO training](https://arxiv.org/abs/2305.18290)** for instruction-tuned models. See [this example](#dpo-training) to train your models (experimental feature). [23/08/03] Now we support training the **Qwen-7B** model in this repo. Try `--model_name_or_path Qwen/Qwen-7B-Chat` and `--lora_target c_attn` arguments to train the Qwen-7B model. Remember to use `--template chatml` argument when you are using the Qwen-7B-Chat model. [23/07/31] Now we support **dataset streaming**. Try `--streaming` and `--max_steps 10000` arguments to load your dataset in streaming mode. [23/07/29] We release two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos ([LLaMA-2](https://huggingface.co/hiyouga/Llama-2-Chinese-13b-chat) / [Baichuan](https://huggingface.co/hiyouga/baichuan-13b-sft)) for details. [23/07/19] Now we support training the **LLaMA-2** models in this repo. Try `--model_name_or_path meta-llama/Llama-2-7b-hf` argument to use the LLaMA-2 model. Remember to use `--template llama2` argument when you are using the LLaMA-2-chat model. [23/07/18] Now we develop an **all-in-one Web UI** for training, evaluation and inference. Try `train_web.py` to fine-tune models in your Web browser. Thank [@KanadeSiina](https://github.com/KanadeSiina) and [@codemayq](https://github.com/codemayq) for their efforts in the development. [23/07/11] Now we support training the **Baichuan-13B** model in this repo. Try `--model_name_or_path baichuan-inc/Baichuan-13B-Base` and `--lora_target W_pack` arguments to train the Baichuan-13B model. Remember to use `--template baichuan` argument when you are using the Baichuan-13B-Chat model. [23/07/09] Now we release **[FastEdit](https://github.com/hiyouga/FastEdit)** ⚡🩹, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow [FastEdit](https://github.com/hiyouga/FastEdit) if you are interested. [23/07/07] Now we support training the **InternLM-7B** model in this repo. Try `--model_name_or_path internlm/internlm-7b` argument to use the InternLM model. Remember to use `--template intern` argument when you are using the InternLM-chat model. [23/07/05] Now we support training the **Falcon-7B/40B** models in this repo. Try `--model_name_or_path tiiuae/falcon-7b` and `--lora_target query_key_value` arguments to use the Falcon model. [23/06/29] We provide a **reproducible example** of training a chat model using instruction-following datasets, see this [Hugging Face Repo](https://huggingface.co/hiyouga/baichuan-7b-sft) for details. [23/06/22] Now we align the [demo API](src/api_demo.py) with the [OpenAI's](https://platform.openai.com/docs/api-reference/chat) format where you can insert the fine-tuned model in **arbitrary ChatGPT-based applications**. [23/06/15] Now we support training the **Baichuan-7B** model in this repo. Try `--model_name_or_path baichuan-inc/Baichuan-7B` and `--lora_target W_pack` arguments to use the Baichuan-7B model. [23/06/03] Now we support quantized training and inference (aka **[QLoRA](https://github.com/artidoro/qlora)**). Try `--quantization_bit 4/8` argument to work with quantized models. [23/05/31] Now we support training the **BLOOM & BLOOMZ** models in this repo. Try `--model_name_or_path bigscience/bloomz-7b1-mt` and `--lora_target query_key_value` arguments to use the BLOOMZ model. ## Supported Models | Model | Model size | Default module | Template | | -------------------------------------------------------- | --------------------------- | ----------------- | --------- | | [LLaMA](https://github.com/facebookresearch/llama) | 7B/13B/33B/65B | q_proj,v_proj | - | | [LLaMA-2](https://huggingface.co/meta-llama) | 7B/13B/70B | q_proj,v_proj | llama2 | | [BLOOM](https://huggingface.co/bigscience/bloom) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - | | [BLOOMZ](https://huggingface.co/bigscience/bloomz) | 560M/1.1B/1.7B/3B/7.1B/176B | query_key_value | - | | [Falcon](https://huggingface.co/tiiuae/falcon-7b) | 7B/40B | query_key_value | - | | [Baichuan](https://github.com/baichuan-inc/Baichuan-13B) | 7B/13B | W_pack | baichuan | | [Baichuan2](https://github.com/baichuan-inc/Baichuan2) | 7B/13B | W_pack | baichuan2 | | [InternLM](https://github.com/InternLM/InternLM) | 7B | q_proj,v_proj | intern | | [Qwen](https://github.com/QwenLM/Qwen-7B) | 7B | c_attn | chatml | | [XVERSE](https://github.com/xverse-ai/XVERSE-13B) | 13B | q_proj,v_proj | xverse | | [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B) | 6B | query_key_value | chatglm2 | - **Default module** is used for the `--lora_target` argument. Please use `python src/train_bash.py -h` to see all available options. - For the "base" models, the `--template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the corresponding template for the "chat" models. ## Supported Training Approaches | Approach | Full-parameter | Partial-parameter | LoRA | QLoRA | | ---------------------- | ------------------ | ------------------ | ------------------ | ------------------ | | Pre-Training | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | Supervised Fine-Tuning | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: | | Reward Modeling | | | :white_check_mark: | :white_check_mark: | | PPO Training | | | :white_check_mark: | :white_check_mark: | | DPO Training | :white_check_mark: | | :white_check_mark: | :white_check_mark: | - Use `--quantization_bit 4/8` argument to enable QLoRA. ## Provided Datasets - For pre-training: - [Wiki Demo (en)](data/wiki_demo.txt) - [RefinedWeb (en)](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) - [StarCoder (en)](https://huggingface.co/datasets/bigcode/starcoderdata) - [Wikipedia (en)](https://huggingface.co/datasets/olm/olm-wikipedia-20221220) - [Wikipedia (zh)](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered) - For supervised fine-tuning: - [Stanford Alpaca (en)](https://github.com/tatsu-lab/stanford_alpaca) - [Stanford Alpaca (zh)](https://github.com/ymcui/Chinese-LLaMA-Alpaca) - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1) - [Self-cognition (zh)](data/self_cognition.json) - [ShareGPT (zh)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT/tree/main/Chinese-instruction-collection) - [Guanaco Dataset (multilingual)](https://huggingface.co/datasets/JosephusCheung/GuanacoDataset) - [BELLE 2M (zh)](https://huggingface.co/datasets/BelleGroup/train_2M_CN) - [BELLE 1M (zh)](https://huggingface.co/datasets/BelleGroup/train_1M_CN) - [BELLE 0.5M (zh)](https://huggingface.co/datasets/BelleGroup/train_0.5M_CN) - [BELLE Dialogue 0.4M (zh)](https://huggingface.co/datasets/BelleGroup/generated_chat_0.4M) - [BELLE School Math 0.25M (zh)](https://huggingface.co/datasets/BelleGroup/school_math_0.25M) - [BELLE Multiturn Chat 0.8M (zh)](https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M) - [Firefly 1.1M (zh)](https://huggingface.co/datasets/YeungNLP/firefly-train-1.1M) - [LIMA (en)](https://huggingface.co/datasets/GAIR/lima) - [CodeAlpaca 20k (en)](https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k) - [Alpaca CoT (multilingual)](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT) - [Web QA (zh)](https://huggingface.co/datasets/suolyer/webqa) - [UltraChat (en)](https://github.com/thunlp/UltraChat) - [WebNovel (zh)](https://huggingface.co/datasets/zxbsmk/webnovel_cn) - [Ad Gen (zh)](https://huggingface.co/datasets/HasturOfficial/adgen) - For reward modeling or DPO training: - [HH-RLHF (en)](https://huggingface.co/datasets/Anthropic/hh-rlhf) - [Open Assistant (multilingual)](https://huggingface.co/datasets/OpenAssistant/oasst1) - [GPT-4 Generated Data (en&zh)](https://github.com/Instruction-Tuning-with-GPT-4/GPT-4-LLM) Please refer to [data/README.md](data/README.md) for details. Some datasets require confirmation before using them, so we recommend logging in with your Hugging Face account using these commands. ```bash pip install --upgrade huggingface_hub huggingface-cli login ``` ## Requirement - Python 3.8+ and PyTorch 1.13.1+ - 🤗Transformers, Datasets, Accelerate, PEFT and TRL - sentencepiece and tiktoken - jieba, rouge-chinese and nltk (used at evaluation) - gradio and matplotlib (used in web_demo.py) - uvicorn, fastapi and sse-starlette (used in api_demo.py) And **powerful GPUs**! ## Getting Started ### Data Preparation (optional) Please refer to `data/example_dataset` for checking the details about the format of dataset files. You can either use a single `.json` file or a [dataset loading script](https://huggingface.co/docs/datasets/dataset_script) with multiple files to create a custom dataset. Note: please update `data/dataset_info.json` to use your custom dataset. About the format of this file, please refer to `data/README.md`. ### Dependence Installation (optional) ```bash git clone https://github.com/hiyouga/LLaMA-Efficient-Tuning.git conda create -n llama_etuning python=3.10 conda activate llama_etuning cd LLaMA-Efficient-Tuning pip install -r requirements.txt ``` If you want to enable the quantized LoRA (QLoRA) on the Windows platform, you will be required to install a pre-built version of `bitsandbytes` library, which supports CUDA 11.1 to 12.1. ```bash pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.39.1-py3-none-win_amd64.whl ``` ### All-in-one Web UI ```bash CUDA_VISIBLE_DEVICES=0 python src/train_web.py ``` We strongly recommend using the all-in-one Web UI for newcomers since it can also generate training scripts **automatically**. Currently the web UI only supports training on **a single GPU**. ### Train on a single GPU #### Pre-Training ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage pt \ --model_name_or_path path_to_llama_model \ --do_train \ --dataset wiki_demo \ --template default \ --finetuning_type lora \ --lora_target q_proj,v_proj \ --output_dir path_to_pt_checkpoint \ --overwrite_cache \ --per_device_train_batch_size 4 \ --gradient_accumulation_steps 4 \ --lr_scheduler_type cosine \ --logging_steps 10 \ --save_steps 1000 \ --learning_rate 5e-5 \ --num_train_epochs 3.0 \ --plot_loss \ --fp16 ``` #### Supervised Fine-Tuning ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage sft \ --model_name_or_path path_to_llama_model \ --do_train \ --dataset alpaca_gpt4_en \ --template default \ --finetuning_type lora \ --lora_target q_proj,v_proj \ --output_dir path_to_sft_checkpoint \ --overwrite_cache \ --per_device_train_batch_size 4 \ --gradient_accumulation_steps 4 \ --lr_scheduler_type cosine \ --logging_steps 10 \ --save_steps 1000 \ --learning_rate 5e-5 \ --num_train_epochs 3.0 \ --plot_loss \ --fp16 ``` #### Reward Modeling ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage rm \ --model_name_or_path path_to_llama_model \ --do_train \ --dataset comparison_gpt4_en \ --template default \ --finetuning_type lora \ --lora_target q_proj,v_proj \ --resume_lora_training False \ --checkpoint_dir path_to_sft_checkpoint \ --output_dir path_to_rm_checkpoint \ --per_device_train_batch_size 2 \ --gradient_accumulation_steps 4 \ --lr_scheduler_type cosine \ --logging_steps 10 \ --save_steps 1000 \ --learning_rate 1e-6 \ --num_train_epochs 1.0 \ --plot_loss \ --fp16 ``` #### PPO Training ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage ppo \ --model_name_or_path path_to_llama_model \ --do_train \ --dataset alpaca_gpt4_en \ --template default \ --finetuning_type lora \ --lora_target q_proj,v_proj \ --resume_lora_training False \ --checkpoint_dir path_to_sft_checkpoint \ --reward_model path_to_rm_checkpoint \ --output_dir path_to_ppo_checkpoint \ --per_device_train_batch_size 2 \ --gradient_accumulation_steps 4 \ --lr_scheduler_type cosine \ --logging_steps 10 \ --save_steps 1000 \ --learning_rate 1e-5 \ --num_train_epochs 1.0 \ --plot_loss \ --fp16 ``` #### DPO Training ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage dpo \ --model_name_or_path path_to_llama_model \ --do_train \ --dataset comparison_gpt4_en \ --template default \ --finetuning_type lora \ --lora_target q_proj,v_proj \ --resume_lora_training False \ --checkpoint_dir path_to_sft_checkpoint \ --output_dir path_to_dpo_checkpoint \ --per_device_train_batch_size 2 \ --gradient_accumulation_steps 4 \ --lr_scheduler_type cosine \ --logging_steps 10 \ --save_steps 1000 \ --learning_rate 1e-5 \ --num_train_epochs 1.0 \ --plot_loss \ --fp16 ``` ### Distributed Training #### Use Huggingface Accelerate ```bash accelerate config # configure the environment accelerate launch src/train_bash.py # arguments (same as above) ```
Example config.yaml for training with DeepSpeed ZeRO-2 ```yaml compute_environment: LOCAL_MACHINE deepspeed_config: gradient_accumulation_steps: 4 gradient_clipping: 0.5 offload_optimizer_device: none offload_param_device: none zero3_init_flag: false zero_stage: 2 distributed_type: DEEPSPEED downcast_bf16: 'no' machine_rank: 0 main_training_function: main mixed_precision: fp16 num_machines: 1 num_processes: 4 rdzv_backend: static same_network: true tpu_env: [] tpu_use_cluster: false tpu_use_sudo: false use_cpu: false ```
#### Use DeepSpeed ```bash deepspeed --num_gpus 8 --master_port=9901 src/train_bash.py \ --deepspeed ds_config.json \ ... # arguments (same as above) ```
Example ds_config.json for training with DeepSpeed ZeRO-2 ```json { "train_micro_batch_size_per_gpu": "auto", "gradient_accumulation_steps": "auto", "gradient_clipping": "auto", "zero_allow_untested_optimizer": true, "fp16": { "enabled": "auto", "loss_scale": 0, "initial_scale_power": 16, "loss_scale_window": 1000, "hysteresis": 2, "min_loss_scale": 1 }, "zero_optimization": { "stage": 2, "allgather_partitions": true, "allgather_bucket_size": 5e8, "reduce_scatter": true, "reduce_bucket_size": 5e8, "overlap_comm": false, "contiguous_gradients": true } } ```
### Export model ```bash python src/export_model.py \ --model_name_or_path path_to_llama_model \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint \ --output_dir path_to_export ``` ### API Demo ```bash python src/api_demo.py \ --model_name_or_path path_to_llama_model \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint ``` Visit `http://localhost:8000/docs` for API documentation. ### CLI Demo ```bash python src/cli_demo.py \ --model_name_or_path path_to_llama_model \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint ``` ### Web Demo ```bash python src/web_demo.py \ --model_name_or_path path_to_llama_model \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint ``` ### Evaluation (BLEU and ROUGE_CHINESE) ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage sft \ --model_name_or_path path_to_llama_model \ --do_eval \ --dataset alpaca_gpt4_en \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint \ --output_dir path_to_eval_result \ --per_device_eval_batch_size 8 \ --max_samples 100 \ --predict_with_generate ``` We recommend using `--per_device_eval_batch_size=1` and `--max_target_length 128` at 4/8-bit evaluation. ### Predict ```bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage sft \ --model_name_or_path path_to_llama_model \ --do_predict \ --dataset alpaca_gpt4_en \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint \ --output_dir path_to_predict_result \ --per_device_eval_batch_size 8 \ --max_samples 100 \ --predict_with_generate ``` ## TODO - [ ] Supporting flash attention ([torch](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) / [xformers](https://github.com/facebookresearch/xformers) / [flashattn](https://github.com/Dao-AILab/flash-attention)). - [ ] Implementing multi-query attention for faster inference. - [ ] Supporting full-parameter RLHF training. ## License This repository is licensed under the [Apache-2.0 License](LICENSE). Please follow the model licenses to use the corresponding model weights: - [LLaMA](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) - [LLaMA-2](https://ai.meta.com/llama/license/) - [BLOOM](https://huggingface.co/spaces/bigscience/license) - [Falcon](LICENSE) - [Baichuan](https://huggingface.co/baichuan-inc/baichuan-7B/resolve/main/baichuan-7B%20%E6%A8%A1%E5%9E%8B%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf) - [Baichuan2](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base/resolve/main/Baichuan%202%E6%A8%A1%E5%9E%8B%E7%A4%BE%E5%8C%BA%E8%AE%B8%E5%8F%AF%E5%8D%8F%E8%AE%AE.pdf) - [InternLM](https://github.com/InternLM/InternLM#open-source-license) - [Qwen](https://huggingface.co/Qwen/Qwen-7B-Chat/blob/main/LICENSE) - [XVERSE](https://github.com/xverse-ai/XVERSE-13B/blob/main/MODEL_LICENSE.pdf) - [ChatGLM2](https://github.com/THUDM/ChatGLM2-6B/blob/main/MODEL_LICENSE) ## Citation If this work is helpful, please kindly cite as: ```bibtex @Misc{llama-efficient-tuning, title = {LLaMA Efficient Tuning}, author = {hiyouga}, howpublished = {\url{https://github.com/hiyouga/LLaMA-Efficient-Tuning}}, year = {2023} } ``` ## Acknowledgement This repo is a sibling of [ChatGLM-Efficient-Tuning](https://github.com/hiyouga/ChatGLM-Efficient-Tuning). They share a similar code structure of efficient tuning on large language models. ## Star History ![Star History Chart](https://api.star-history.com/svg?repos=hiyouga/LLaMA-Efficient-Tuning&type=Date)