metadata
library_name: peft
datasets:
- liuhaotian/LLaVA-Pretrain
- liuhaotian/LLaVA-Instruct-150K
pipeline_tag: visual-question-answering
Model
llava-internlm-chat-7b-clip-vit-large-p14-336 is a LLaVA model fine-tuned from InternLM-Chat-7B and CLIP-ViT-Large-patch14-336 with LLaVA-Pretrain and LLaVA-Instruct by XTuner.
Quickstart
Installation
pip install -U 'xtuner[deepspeed]'
Chat
xtuner chat internlm/internlm-chat-7b \
--visual-encoder openai/clip-vit-large-patch14 \
--llava xtuner/llava-internlm-chat-7b-clip-vit-large-p14-336 \
--prompt-template internlm_chat \
--image $IMAGE_PATH
Training
- Alignment module pretraining (saved by default in
./work_dirs/)
NPROC_PER_NODE=8 xtuner train llava_internlm_chat_7b_clip_vit_large_p14_336_e1_gpu8_pretrain --deepspeed deepspeed_zero2
- Instruction following fine-tuning (saved by default in
./work_dirs/)
NPROC_PER_NODE=8 xtuner train llava_internlm_chat_7b_qlora_clip_vit_large_p14_336_lora_e1_gpu8_finetune --deepspeed deepspeed_zero2
MMBench Evaluation
XTuner integrates the MMBench evaluation, and you can perform evaluations with the following command!
xtuner mmbench internlm/internlm-chat-7b \
--visual-encoder openai/clip-vit-large-patch14 \
--llava xtuner/llava-internlm-chat-7b-clip-vit-large-p14-336 \
--prompt-template internlm_chat \
--data-path $MMBENCH_DATA_PATH \
--language en \
--work-dir $RESULT_PATH
After the evaluation is completed, if it's a development set, it will directly print out the results; If it's a test set, you need to submit mmbench_result.xlsx to the official MMBench for final evaluation to obtain precision results!
Citation
@misc{2023xtuner,
title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
author={XTuner Contributors},
howpublished = {\url{https://github.com/InternLM/xtuner}},
year={2023}
}