metadata
datasets:
- Lin-Chen/ShareGPT4V
pipeline_tag: image-text-to-text
library_name: xtuner
Model
llava-llama-3-8b-v1_1 is a LLaVA model fine-tuned from meta-llama/Meta-Llama-3-8B-Instruct and CLIP-ViT-Large-patch14-336 with ShareGPT4V-PT and InternVL-SFT by XTuner.
Results
Quickstart
Installation
pip install 'git+https://github.com/InternLM/xtuner.git#egg=xtuner[deepspeed]'
Chat
xtuner chat xtuner/llava-llama-3-8b-v1_1 \
--visual-encoder openai/clip-vit-large-patch14-336 \
--llava xtuner/llava-llama-3-8b-v1_1 \
--prompt-template llama3_chat \
--image $IMAGE_PATH
MMBench Evaluation
XTuner integrates the MMBench evaluation, and you can perform evaluations with the following command!
xtuner mmbench xtuner/llava-llama-3-8b-v1_1 \
--visual-encoder openai/clip-vit-large-patch14-336 \
--llava xtuner/llava-llama-3-8b-v1_1 \
--prompt-template llama3_chat \
--data-path $MMBENCH_DATA_PATH \
--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!
Training
- Pretrain (saved by default in
./work_dirs/llava_llama3_8b_instruct_clip_vit_large_p14_336_e1_gpu8_sharegpt4v_pretrain/
)
NPROC_PER_NODE=8 xtuner train llava_llama3_8b_instruct_clip_vit_large_p14_336_e1_gpu8_sharegpt4v_pretrain --deepspeed deepspeed_zero2 --seed 1234
- Fine-tune (saved by default in
./work_dirs/llava_llama3_8b_instruct_full_clip_vit_large_p14_336_lora_e1_gpu8_internvl_finetune/
)
NPROC_PER_NODE=8 xtuner train llava_llama3_8b_instruct_full_clip_vit_large_p14_336_lora_e1_gpu8_internvl_finetune --deepspeed deepspeed_zero2 --seed 1234
Citation
@misc{2023xtuner,
title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
author={XTuner Contributors},
howpublished = {\url{https://github.com/InternLM/xtuner}},
year={2023}
}