LMFlow

English | 简体中文 | Español | 日本語 | 한국어 | हिंदी

An extensible, convenient, and efficient toolbox for finetuning large machine learning models, designed to be user-friendly, speedy and reliable, and accessible to the entire community.

Latest News

• [2024-12-02] Support Hymba, a new family of small language models featuring a hybrid-head parallel architecture. Check out Post-training Hymba for more details.
• [2024-07-01] 🏆 LMFlow receives the Best Demo Paper Award at NAACL 2024! 🎉
• [2024-06-30] Expanding Optimization Options! We now support custom optimizer training with a variety of optimizers. Dive into the details and try out the new features with our updated script at custom_optimizers.
• [2024-04-25] :rocket: Support conversation template! We've preset the latest Llama-3 and Phi-3 conversation templates as well as some frequently used templates such as chatml (see all templates here), and we are working on adding more preset templates. Adding corresponding --conversation_template in the shell script and you are all set! :rocket:
• [2024-03-27] Support LISA, enabling 7B training in 24G memory without offloading!
• [2023-09-11] Support speculative decoding. Check out speculative_decoding for the usage and acceleration details.
• [2023-08-14] Support long context inference with position interpolation (Linear & NTK scaling ) for LLaMA models. Check out postion_interpolation for more details.
• [2023-08-07] Support Flash Attention-2. Check out flash_attention for more details.

Table of Contents

• LMFlow
  • Latest News
  • Table of Contents
  • Supported Models
  • Quick Start
    • Setup
    • Prepare Dataset
    • Finetuning
      • Full Finetuning
      • LISA
      • LoRA
    • Inference
    • Deployment
    • Evaluation
  • Supported Features
  • Support
  • License
  • Citation

Supported Models

Quick Start

Setup

Our package has been tested on Linux OS (Ubuntu 20.04). Other OS platforms (MacOS, Windows) are not fully tested, where you may encounter unexpected errors. If you are using LMFlow for the first time, we recommend you to try on a Linux machine or Google Colab.

CUDA versions 10.3-11.7 are supported in versions v0.0.5 or older. For CUDA versions greater than 11.7, one can use our stable branch >= v0.0.6.

git clone -b v0.0.9 https://github.com/OptimalScale/LMFlow.git
cd LMFlow
conda create -n lmflow python=3.9 -y
conda activate lmflow
conda install mpi4py
pip install -e .

[!TIP] We use WandB to track and visualize the training process by default. Before running the training scripts, users may need to log in to WandB using the command:

wandb login

For detailed instructions, refer to the WandB Quickstart Guide. Step 1 (registration) and Step 2 (login using your WandB API key) should be sufficient to set up your environment.

Disabling wandb

One can disable wandb by either:

1. Adding environment variable before running the training command.

export WANDB_MODE=disabled

2. OR, specifying the integrations to report the results and logs to. In the training script, add:

--report_to none \

Prepare Dataset

Please refer to our doc.

Finetuning

Full Finetuning

Full training updates all the parameters to finetune a language model. Here is an example to finetune a GPT-2 base model.

cd data && ./download.sh alpaca && cd -

bash ./scripts/run_finetune.sh \
  --model_name_or_path gpt2 \
  --dataset_path data/alpaca/train_conversation \
  --output_model_path output_models/finetuned_gpt2

[!TIP] For conversation dataset, specify a conversation template for better performance by adding --conversation_template to the command.

Llama-3-8B conversation dataset example

cd data && ./download.sh alpaca && cd -

bash ./scripts/run_finetune.sh \
 --model_name_or_path meta-llama/Meta-Llama-3-8B \
 --dataset_path data/alpaca/train_conversation \
 --conversation_template llama3 \
 --output_model_path output_models/finetuned_llama3_8b

LISA

LISA is a memory-efficient finetuning algorithm that allows tradeoff between memory and the number of randomly unfreezed layers. This script currently is only tested in single gpus. Please stay tuned for our latest updates :smile:

cd data && ./download.sh alpaca && cd -

bash ./scripts/run_finetune_with_lisa.sh \
  --model_name_or_path meta-llama/Llama-2-7b-hf \
  --dataset_path data/alpaca/train_conversation \
  --output_model_path output_models/finetuned_llama2_7b \
  --lisa_activated_layers 1 \
  --lisa_interval_steps 20

[!TIP]

Llama-2-7B conversation dataset example

cd data && ./download.sh alpaca && cd -

bash ./scripts/run_finetune_with_lisa.sh \
 --model_name_or_path meta-llama/Llama-2-7b-hf \
 --dataset_path data/alpaca/train_conversation \
 --conversation_template llama2 \
 --output_model_path output_models/finetuned_llama2_7b_lisa \
 --lisa_activated_layers 1 \
 --lisa_interval_steps 20

LoRA

LoRA is a parameter-efficient finetuning algorithm and is more efficient than full finetuning.

cd data && ./download.sh alpaca && cd -

bash ./scripts/run_finetune_with_lora.sh \
  --model_name_or_path facebook/galactica-1.3b \
  --dataset_path data/alpaca/train_conversation \
  --output_lora_path output_models/finetuned_galactica_lora

[!TIP]

Llama-2-7B conversation dataset example

cd data && ./download.sh alpaca && cd -

bash ./scripts/run_finetune_with_lora.sh \
 --model_name_or_path meta-llama/Llama-2-7b-hf \
 --dataset_path data/alpaca/train_conversation \
 --conversation_template llama2 \
 --output_model_path output_models/finetuned_llama2_7b_lora \

Merge LoRA Weight

Merge LoRA weight and the base model into one using:

bash ./scripts/run_merge_lora.sh \
 --model_name_or_path Qwen/Qwen1.5-1.8B \
 --lora_model_path output_models/lora \
 --output_model_path output_models/lora_merged \

Inference

After finetuning, you can run the following command to chat with the model.

bash ./scripts/run_chatbot.sh output_models/finetuned_gpt2

[!TIP] We recommend using vLLM for faster inference.

Faster inference using vLLM

bash ./scripts/run_vllm_inference.sh \
  --model_name_or_path Qwen/Qwen2-0.5B \
  --dataset_path data/alpaca/test_conversation \
  --output_dir data/inference_results \

Deployment

If you want to deploy your own model locally, we provide a gradio-based UI for building chatbots. Running the following command will launch the demo for robin-7b:

pip install gradio
python ./examples/chatbot_gradio.py --deepspeed configs/ds_config_chatbot.json --model_name_or_path YOUR-LLAMA  --lora_model_path ./robin-7b --prompt_structure "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.###Human: {input_text}###Assistant:"       --end_string "#" --max_new_tokens 200

Evaluation

LMFlow Benchmark is an automatic evaluation framework for open-source large language models. We use negative log likelihood (NLL) as the metric to evaluate different aspects of a language model: chitchat, commonsense reasoning, and instruction following abilities.

You can directly run the LMFlow benchmark evaluation to obtain the results to participate in the LLM comparision. For example, to run GPT2 XL, one may execute

bash ./scripts/run_benchmark.sh --model_name_or_path gpt2-xl

--model_name_or_path is required, you may fill in huggingface model name or local model path here.

To check the evaluation results, you may check benchmark.log in ./output_dir/gpt2-xl_lmflow_chat_nll_eval, ./output_dir/gpt2-xl_all_nll_eval and ./output_dir/gpt2-xl_commonsense_qa_eval.

Supported Features

Support

If you need any help, please submit a Github issue.

License

The code included in this project is licensed under the Apache 2.0 license. If you wish to use the codes and models included in this project for commercial purposes, please sign this document to obtain authorization.

Citation

If you find this repository useful, please consider giving ⭐ and citing our paper:

@article{diao2023lmflow,
  title={Lmflow: An extensible toolkit for finetuning and inference of large foundation models},
  author={Diao, Shizhe and Pan, Rui and Dong, Hanze and Shum, Ka Shun and Zhang, Jipeng and Xiong, Wei and Zhang, Tong},
  journal={arXiv preprint arXiv:2306.12420},
  year={2023}
}

@article{dong2023raft,
  title={Raft: Reward ranked finetuning for generative foundation model alignment},
  author={Dong, Hanze and Xiong, Wei and Goyal, Deepanshu and Pan, Rui and Diao, Shizhe and Zhang, Jipeng and Shum, Kashun and Zhang, Tong},
  journal={arXiv preprint arXiv:2304.06767},
  year={2023}
}

@article{pan2024lisa,
  title={LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning}, 
  author={Pan, Rui and Liu, Xiang and Diao, Shizhe and Pi, Renjie and Zhang, Jipeng and Han, Chi and Zhang, Tong},
  journal={arXiv preprint arXiv:2403.17919},
  year={2024}
}