LZHgrla's picture
Update README.md
4ee7091 verified
|
raw
history blame
4.83 kB
metadata
datasets:
  - Lin-Chen/ShareGPT4V
pipeline_tag: image-to-text

Generic badge

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 GGUF format. LLM in fp16 precision is coming soon.

Resources:

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

Image
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

Download models

# mmproj
wget https://huggingface.co/xtuner/llava-phi-3-mini-gguf/resolve/main/mmproj-model-f16.gguf

# int4 llm
wget https://huggingface.co/xtuner/llava-phi-3-mini-gguf/resolve/main/ggml-model-int4.gguf

Build environment

  1. Build llama.cpp (docs) .
  2. Build ./llava-cli (docs).

Chat with ./llava-cli

cd ./llava-phi-3-mini-gguf

# int4
./llava-cli -m ggml-model-int4.gguf --mmproj mmproj-model-f16.gguf --image YOUR_IMAGE.jpg -c 4096

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}
}