LLaMA Efficient Tuning

Join our WeChat.

[ English | ]

Changelog

[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 100 arguments to stream your dataset.

[23/07/29] We release two instruction-tuned 13B models at Hugging Face. See these Hugging Face Repos (LLaMA-2 / Baichuan) 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 and @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, an easy-to-use package for editing the factual knowledge of large language models efficiently. Please follow 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 for details.

[23/06/22] Now we align the demo API with the OpenAI's 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). 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

• LLaMA (7B/13B/33B/65B)
• LLaMA-2 (7B/13B/70B)
• BLOOM & BLOOMZ (560M/1.1B/1.7B/3B/7.1B/176B)
• Falcon (7B/40B)
• Baichuan (7B/13B)
• InternLM (7B)
• Qwen (7B)

Supported Training Approaches

• (Continually) pre-training
  • Full-parameter tuning
  • Partial-parameter tuning
  • LoRA
  • QLoRA
• Supervised fine-tuning
  • Full-parameter tuning
  • Partial-parameter tuning
  • LoRA
  • QLoRA
• RLHF
  • LoRA
  • QLoRA

Provided Datasets

• For pre-training:
  • Wiki Demo (en)
  • RefinedWeb (en)
  • StarCoder (en)
  • Wikipedia (en)
  • Wikipedia (zh)
• For supervised fine-tuning:
  • Stanford Alpaca (en)
  • Stanford Alpaca (zh)
  • GPT-4 Generated Data (en&zh)
  • Open Assistant (multilingual)
  • Self-cognition (zh)
  • ShareGPT (zh)
  • RefGPT (zh)
  • Guanaco Dataset (multilingual)
  • BELLE 2M (zh)
  • BELLE 1M (zh)
  • BELLE 0.5M (zh)
  • BELLE Dialogue 0.4M (zh)
  • BELLE School Math 0.25M (zh)
  • BELLE Multiturn Chat 0.8M (zh)
  • Firefly 1.1M (zh)
  • LIMA (en)
  • CodeAlpaca 20k (en)
  • Alpaca CoT (multilingual)
  • Web QA (zh)
  • UltraChat (en)
  • WebNovel (zh)
• For reward modelling:
  • HH-RLHF (en)
  • Open Assistant (multilingual)
  • GPT-4 Generated Data (en&zh)

Please refer to 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 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 lfs install 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

Currently the web UI only supports training on a single GPU.

(Continually) Pre-Training

bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage pt \ --model_name_or_path path_to_your_model \ --do_train \ --dataset wiki_demo \ --template default \ --finetuning_type lora \ --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_your_model \ --do_train \ --dataset alpaca_gpt4_en \ --template default \ --finetuning_type lora \ --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

Remember to specify --lora_target W_pack if you are using Baichuan models.

Reward Model Training

bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage rm \ --model_name_or_path path_to_your_model \ --do_train \ --dataset comparison_gpt4_en \ --template default \ --finetuning_type lora \ --resume_lora_training False \ --checkpoint_dir path_to_sft_checkpoint \ --output_dir path_to_rm_checkpoint \ --per_device_train_batch_size 4 \ --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

PPO Training (RLHF)

bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage ppo \ --model_name_or_path path_to_your_model \ --do_train \ --dataset alpaca_gpt4_en \ --template default \ --finetuning_type lora \ --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

Distributed Training

bash accelerate config # configure the environment accelerate launch src/train_bash.py # arguments (same as above)

Example configuration for full-tuning 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 ```

Evaluation (BLEU and ROUGE_CHINESE)

bash CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \ --stage sft \ --model_name_or_path path_to_your_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_your_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

API Demo

bash python src/api_demo.py \ --model_name_or_path path_to_your_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_your_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_your_model \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint

Export model

bash python src/export_model.py \ --model_name_or_path path_to_your_model \ --template default \ --finetuning_type lora \ --checkpoint_dir path_to_checkpoint \ --output_dir path_to_export

TODO

• [ ] Supporting flash attention (torch / xformers / flashattn).
• [ ] Implementing multi-query attention for faster inference.
• [ ] Supporting full-parameter RLHF training.

License

This repository is licensed under the Apache-2.0 License.

Please follow the model licenses to use the corresponding model weights:

• LLaMA
• LLaMA-2
• BLOOM
• Falcon
• Baichuan
• InternLM
• Qwen

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. They share a similar code structure of efficient tuning on large language models.

Star History