English | 简体中文

We recommend two projects to fine-tune InternLM.

1. XTuner is an efficient, flexible and full-featured toolkit for fine-tuning large models.

2. InternEvo is a powerful training framework that supports large-scale pre-training and finetuning.

1. Support LLM, VLM pre-training / fine-tuning on almost all GPUs. XTuner is capable of fine-tuning InternLM2-7B on a single 8GB GPU, as well as multi-node fine-tuning of models exceeding 70B.
2. Support various training algorithms (QLoRA, LoRA, full-parameter fune-tune), allowing users to choose the most suitable solution for their requirements.
3. Compatible with DeepSpeed 🚀, easily utilizing a variety of ZeRO optimization techniques.
4. The output models can seamlessly integrate with deployment and server toolkit (LMDeploy), and large-scale evaluation toolkit (OpenCompass, VLMEvalKit).

• It is recommended to build a Python 3.10 virtual environment using conda

  conda create --name xtuner-env python=3.10 -y
  conda activate xtuner-env

• Install XTuner with DeepSpeed integration

  pip install -U 'xtuner[deepspeed]>=0.1.13'

XTuner supports the efficient fine-tune (e.g., QLoRA) for InternLM2.

• Step 0, prepare the config. XTuner provides many ready-to-use configs and we can view all configs of InternLM2 by

  xtuner list-cfg -p internlm2

  Or, if the provided configs cannot meet the requirements, please copy the provided config to the specified directory and make specific modifications by

  xtuner copy-cfg ${CONFIG_NAME} ${SAVE_PATH}
  vi ${SAVE_PATH}/${CONFIG_NAME}_copy.py

• Step 1, start fine-tuning.

  xtuner train ${CONFIG_NAME_OR_PATH}

  For example, we can start the QLoRA fine-tuning of InternLM2-Chat-7B with oasst1 dataset by

  # On a single GPU
  xtuner train internlm2_chat_7b_qlora_oasst1_e3 --deepspeed deepspeed_zero2
  # On multiple GPUs
  (DIST) NPROC_PER_NODE=${GPU_NUM} xtuner train internlm2_chat_7b_qlora_oasst1_e3 --deepspeed deepspeed_zero2
  (SLURM) srun ${SRUN_ARGS} xtuner train internlm2_chat_7b_qlora_oasst1_e3 --launcher slurm --deepspeed deepspeed_zero2

  • --deepspeed means using DeepSpeed 🚀 to optimize the training. XTuner comes with several integrated strategies including ZeRO-1, ZeRO-2, and ZeRO-3. If you wish to disable this feature, simply remove this argument.

• Step 2, convert the saved PTH model (if using DeepSpeed, it will be a directory) to HuggingFace model, by

  xtuner convert pth_to_hf ${CONFIG_NAME_OR_PATH} ${PTH} ${SAVE_PATH}

XTuner provides tools to chat with pretrained / fine-tuned large models.

xtuner chat ${NAME_OR_PATH_TO_LLM} [optional arguments]

For example, we can start the chat with

InternLM2-Chat-7B with adapter trained from oasst1:

xtuner chat internlm/internlm2-chat-7b --adapter xtuner/internlm2-chat-7b-qlora-oasst1 --prompt-template internlm2_chat

LLaVA-InternLM2-7B:

xtuner chat internlm/internlm2-chat-7b --visual-encoder openai/clip-vit-large-patch14-336 --llava xtuner/llava-internlm2-7b --prompt-template internlm2_chat --image $IMAGE_PATH

[TODO]