/LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Primary LanguagePythonApache License 2.0Apache-2.0

LMFlow

LMFlow

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

Website Code License Python 3.9+ Doc Embark slack badge WeChat badge

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.

Large Model for All. See our vision.

LMFlow-features

Latest News

Demos

We provide four kinds of demos which include

  • Online Service: If you don't want to run any code and just want to try our models, we deploy our instruction-tuned LLaMA you to have a try.
  • Colab Chatbot (shell): An interactive shell-based chatbot for you to easily deploy a chatbot on colab.
  • Colab Chatbot (web): An interactive web-based chatbot for you to easily deploy your own chatbot on colab.
  • Local Deploy: We also provide a way for you to deploy your model/chatbot locally, which means you can deploy much larger model than previous three methods if you have enough resource.

Code License colab badge colab badge colab badge

Online Service

Welcome to visit our web service. We deploy LLaMA-7B-tuned model online for preview. Due to the high website traffic, sometimes the website may fail to respond. You can also deploy the chatbot following Local Deploy.

Colab chatbot (shell)

We provide a simple shell demo of chatbot with Google Colab's T4/P100/V100 GPU. Notice that the provided gpt-neo-2.7b model is a rather weak model, which only supports English and may sometimes generate unsatisfactory responses. To improve the performance, users can use their own dataset to finetune and obtain a better model with LMFlow. One can also try other available decoder-only models provided in 🤗 Hugging Face, by

./scripts/run_chatbot.sh {another-model-name}

Colab chatbot (web)

We provide a simple web demo of chatbot with Google Colab's T4/P100/V100 GPU. Notice that the provided gpt-neo-2.7b model is a rather weak model, which only supports English and may sometimes generate unsatisfactory responses.

Local Deploy

If you have resources and want to deploy your own model locally. We provide you an easy way to run a flask server to launch a backend (to further provide services to other frontend) and an interactive web frontend (to let you communicate directly) by

./scripts/run_app.sh

We also 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

We also hosted it on Hugging Face Space.

Colab RAFT-diffusion

We also provide a simple demo to display the effectiveness of RAFT algorithm on diffusion models. You can refer to either Colab link or experimental/RAFT-diffusion/SD256-RAFT.ipynb. The support of multi-modal training of LMFlow is under development.

Medical Performance

PubMedQA (ID) MedQA-USMLE (OOD) MedMCQA (ID) Average
Human (pass) 60.0 50.0
Human (expert) 78.0 87.0 90.0 85.0
InstructGPT 175B 73.2 46.0 44.0 54.4
ChatGPT 63.9 57.0 44.7 55.2
LLaMA 7B 5.2 27.1 24.3 18.9
LLaMA 33B 1.8 43.4 30.3 25.2
Task-tuned LLaMA 7B (Full) 75.1 44.5 49.9 56.5
Task-tuned LLaMA 33B (LoRA) 74.0 51.3 50.2 58.5

The LLaMA 33B (LoRA) performance is achieved with only ~16h finetuning on the training split of PubMedQA and MedMCQA with a single 8 * A100 server. For more performance, including instruction tuning results, please refer to our Documentation.

Model Zoo

We open-sourced the trained checkpoints to everyone for further training and inference.

Model
Base Model		 Robin-7B ⭐
LLaMA-7B		 Robin-13B
LLaMA-13B		 Robin-33B
LLaMA-33B		 Robin-65B
LLaMA-65B
Model
Base Model		 Robin-7B-medical
LLaMA-7B		 Robin-13B-medical
LLaMA-13B		 Robin-33B-medical
LLaMA-33B		 Robin-65B-medical
LLaMA-65B
Model
Base Model		 Parakeets-2.7B ⭐
GPT-NEO-2.7B		 Cockatoo-3B
StableLM-3B		 Cockatoo-7B ⭐
StableLM-7B

Supported Pipelines

Pipelines Status
Task Tuning ✅ Supported
Instruction Tuning ✅ Supported
Parameter-Efficient Tuning ✅ Supported
Alignment Tuning ✅ Supported
Large Model Inference ✅ Supported

Supported Models

Seamlessly supported all the decoder models in 🤗 Hugging Face. LLaMA, GPT2, GPT-Neo, Galactica, have been fully tested. We will support encoder models soon.

1.Setup

Our package has been fully tested on Linux OS (Ubuntu 20.04). Other OS platforms (MacOS, Windows) are not fully tested. You may encounter some unexpected errors. You may try it first on a Linux machine or use Google Colab to experience it.

git clone 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 .

2.Prepare Dataset

Please refer to our doc.

3. Running Scripts

3.1 Finetuning

You can run scripts/run_finetune.sh to finetune a GPT-2 base model

./scripts/run_finetune.sh

If you would like to provide arguments for deepspeed to reflect your machine settings, you may pass the corresponding deepspeed arguments to the script. For example,

./scripts/run_finetune.sh "--num_gpus=8 --master_port 10001"

To enable LoRA finetuning, you may refer to

./scripts/run_finetune_with_lora.sh

which can be run in similar manner.

For detailed configurations, one may modify these scripts directly. These scripts actually just call python script examples/finetune.py, which can be run in following manner,

deepspeed ${deepspeed_args} \
  examples/finetune.py \
    --deepspeed configs/ds_config_zero3.json \
    --bf16 \
    --run_name finetune_with_lora \
    --model_name_or_path facebook/galactica-1.3b \
    --num_train_epochs 0.01 \
    --learning_rate 2e-5 \
    --dataset_path ${dataset_path} \
    --per_device_train_batch_size 1 \
    --per_device_eval_batch_size 1 \
    --validation_split_percentage 0 \
    --logging_steps 20 \
    --block_size 512 \
    --do_train \
    --output_dir output_models/finetune \
    --overwrite_output_dir \
    --ddp_timeout 72000 \
    --save_steps 5000 \
    --dataloader_num_workers 1

Here we set number of epochs --num_train_epochs to 0.01 so that the finetuning process can be finished quickly. If you wish to obtain a model with better performance, feel free to adjust those hyperparameters. You may run

python examples/finetune.py -h

Note: In the case of a small training data set, the value of block_size needs to be reduced, otherwise there will be no samples available in the Epoch iterator.

to view all possible finetuning arguments. The finetuned model checkpoint will be saved in the argument specified by --output_dir, which is output_models/finetune in the above example. We follow Alpaca and Vicuna in the model tuning process and serve the model in our web service.

3.2 Evaluation

One can directly run evaluation with an existing Hugging Face model, e.g. to run GPT2 large, one may execute

./scripts/run_evaluation.sh

or run the corresponding python script

CUDA_VISIBLE_DEVICES=0 \
    deepspeed examples/evaluate.py \
    --answer_type medmcqa \
    --model_name_or_path gpt2-large \
    --dataset_path data/MedQA-USMLE/validation \
    --deepspeed examples/ds_config.json

To load the finetuned model, specify --model_name_or_path with the saved model checkpoint directory path.

For LoRA finetuned models, one may refer to

./scripts/run_evaluation_with_lora.sh

Those scripts invoke the examples examples/*.py built based on our APIs. For more API-related examples, one may refer to the methods in the unittest tests.

3.3 LMFlow Benchmark

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

./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.

4. Additional Notes

4.1 LLaMA Checkpoint

Please refer to our doc.

4.2 DeepSpeed Config

You can config the deepspeed under configs. Details can be referred at DeepSpeed Configuration

4.3 LLaMA Inference on CPU

Thanks to the great efforts of llama.cpp. It is possible for everyone to run their LLaMA models on CPU by 4-bit quantization. We provide a script to convert LLaMA LoRA weights to .pt files. You only need to use convert-pth-to-ggml.py in llama.cpp to perform quantization.

5. Model Release

5.1 Medical Model Checkpoints

You can run following script to download our medical model checkpoints :

cd output_models
bash download.sh medical_ckpt
cd -

You can also directly download our model via google drive link : medical_ckpt.tar.gz

5.2 Instruction Model Checkpoints

Similarly, you can run following script to download our instruction model checkpoints :

cd output_models
bash download.sh instruction_ckpt
cd -

You can also directly download our model via google drive link : instruction_ckpt.tar.gz

5.3 Reproduce the result

After downloading the model checkpoints, you can merge the lora model into the base model via

python examples/merge_lora.py \
    --model_name_or_path {huggingface-model-name-or-path-to-base-model} \
    --lora_model_path {path-to-lora-model} \
    --output_model_path {path-to-merged-model}

Or you can replace the --lora_model_path with output_models/instruction_ckpt/llama7b-lora (example for llama-7b for instruction) and replace --model_name_or_path with your converted llama model inside LMFlow/scripts/run_evaluation_with_lora.sh and run this shell script to reproduce the result.

For full model deltas, such as robin-7b-v2-delta, you may use the delta merge script to obtain the full model,

python utils/apply_delta.py \
    --base-model-path {huggingface-model-name-or-path-to-base-model} \
    --delta-path {path-to-delta-model} \
    --target-model-path {path-to-merged-model}

Then you can check the model performance at our Doc.

Documentation

Please refer to our Documentation for more API reference and experimental results.

Vision

Hello there! We are excited to announce the upcoming release of our code repository that includes a complete LLM training process, enabling users to quickly build their own language models and train them effectively.

Our code repository is not just a simple model; it includes the complete training workflow, model optimization, and testing tools. You can use it to build various types of language models, including conversation models, question-answering models, and text generation models, among others.

Moreover, we aim to create an open and democratic LLM sharing platform where people can share their checkpoints and experiences to collectively improve the skills of the community. We welcome anyone who is interested in LLM to participate and join us in building an open and friendly community!

Whether you are a beginner or an expert, we believe that you can benefit from this platform. Let's work together to build a vibrant and innovative LLM community!

Embark slack badge WeChat badge

Acknowledgement

LMFlow draws inspiration from various studies, including but not limited to:

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.

Contributors

Citation

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

@misc{lmflow,
  author = {Shizhe Diao and Rui Pan and Hanze Dong and KaShun Shum and Jipeng Zhang and Wei Xiong and Tong Zhang},
  title = {LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://optimalscale.github.io/LMFlow/}},
}