xtuner/llava-phi-3-mini-xtuner

Model

llava-phi-3-mini is a LLaVA model fine-tuned from microsoft/Phi-3-mini-4k-instruct and CLIP-ViT-Large-patch14-336 with ShareGPT4V-PT and InternVL-SFT by XTuner.

Note: This model is in XTuner LLaVA format.

Resources:

• GitHub: xtuner
• HuggingFace LLaVA format model: xtuner/llava-phi-3-mini-hf
• Official LLaVA format model: xtuner/llava-phi-3-mini
• GGUF LLaVA model: xtuner/llava-phi-3-mini-gguf

Details

Model	Visual Encoder	Projector	Resolution	Pretraining Strategy	Fine-tuning Strategy	Pretrain Dataset	Fine-tune Dataset	Pretrain Epoch	Fine-tune Epoch
LLaVA-v1.5-7B	CLIP-L	MLP	336	Frozen LLM, Frozen ViT	Full LLM, Frozen ViT	LLaVA-PT (558K)	LLaVA-Mix (665K)	1	1
LLaVA-Llama-3-8B	CLIP-L	MLP	336	Frozen LLM, Frozen ViT	Full LLM, LoRA ViT	LLaVA-PT (558K)	LLaVA-Mix (665K)	1	1
LLaVA-Llama-3-8B-v1.1	CLIP-L	MLP	336	Frozen LLM, Frozen ViT	Full LLM, LoRA ViT	ShareGPT4V-PT (1246K)	InternVL-SFT (1268K)	1	1
LLaVA-Phi-3-mini	CLIP-L	MLP	336	Frozen LLM, Frozen ViT	Full LLM, Full ViT	ShareGPT4V-PT (1246K)	InternVL-SFT (1268K)	1	2

Results

Model	MMBench Test (EN)	MMMU Val	SEED-IMG	AI2D Test	ScienceQA Test	HallusionBench aAcc	POPE	GQA	TextVQA	MME	MMStar
LLaVA-v1.5-7B	66.5	35.3	60.5	54.8	70.4	44.9	85.9	62.0	58.2	1511/348	30.3
LLaVA-Llama-3-8B	68.9	36.8	69.8	60.9	73.3	47.3	87.2	63.5	58.0	1506/295	38.2
LLaVA-Llama-3-8B-v1.1	72.3	37.1	70.1	70.0	72.9	47.7	86.4	62.6	59.0	1469/349	45.1
LLaVA-Phi-3-mini	69.2	41.4	70.0	69.3	73.7	49.8	87.3	61.5	57.8	1477/313	43.7

Quickstart

Installation

pip install 'git+https://github.com/InternLM/xtuner.git#egg=xtuner[deepspeed]'

Chat

xtuner chat xtuner/llava-phi-3-mini-xtuner \
  --llava xtuner/llava-phi-3-mini-xtuner \
  --prompt-template phi3_chat \
  --image $IMAGE_PATH

MMBench Evaluation

XTuner integrates the MMBench evaluation, and you can perform evaluations with the following command!

xtuner mmbench xtuner/llava-phi-3-mini-xtuner \
  --llava xtuner/llava-phi-3-mini-xtuner \
  --prompt-template phi3_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!

Reproduce

Please refer to docs.

Citation

@misc{2023xtuner,
    title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
    author={XTuner Contributors},
    howpublished = {\url{https://github.com/InternLM/xtuner}},
    year={2023}
}