🚀 llava-phi-3-mini模型
llava-phi-3-mini是一款圖像到文本生成的模型,它基於特定的預訓練模型和數據集進行微調,能夠有效處理圖像相關的文本生成任務,為圖像理解和信息提取提供了強大的支持。
🚀 快速開始
通過pipeline
進行對話
from transformers import pipeline
from PIL import Image
import requests
model_id = "xtuner/llava-phi-3-mini-hf"
pipe = pipeline("image-to-text", model=model_id, device=0)
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
image = Image.open(requests.get(url, stream=True).raw)
prompt = "<|user|>\n<image>\nWhat does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud<|end|>\n<|assistant|>\n"
outputs = pipe(image, prompt=prompt, generate_kwargs={"max_new_tokens": 200})
print(outputs)
>>> [{'generated_text': '\nWhat does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud (1) lava'}]
通過純transformers
進行對話
import requests
from PIL import Image
import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration
model_id = "xtuner/llava-phi-3-mini-hf"
prompt = "<|user|>\n<image>\nWhat are these?<|end|>\n<|assistant|>\n"
image_file = "http://images.cocodataset.org/val2017/000000039769.jpg"
model = LlavaForConditionalGeneration.from_pretrained(
model_id,
torch_dtype=torch.float16,
low_cpu_mem_usage=True,
).to(0)
processor = AutoProcessor.from_pretrained(model_id)
raw_image = Image.open(requests.get(image_file, stream=True).raw)
inputs = processor(prompt, raw_image, return_tensors='pt').to(0, torch.float16)
output = model.generate(**inputs, max_new_tokens=200, do_sample=False)
print(processor.decode(output[0][2:], skip_special_tokens=True))
>>> What are these? These are two cats sleeping on a pink couch.
復現實驗
請參考文檔。
✨ 主要特性
📚 詳細文檔
模型信息
llava-phi-3-mini是一個LLaVA模型,由XTuner基於特定的預訓練模型和數據集進行微調得到。
注意:該模型採用HuggingFace LLaVA格式。
相關資源:
模型細節
模型 |
視覺編碼器 |
投影器 |
分辨率 |
預訓練策略 |
微調策略 |
預訓練數據集 |
微調數據集 |
預訓練輪數 |
微調輪數 |
LLaVA-v1.5-7B |
CLIP-L |
MLP |
336 |
凍結大語言模型(LLM),凍結視覺模型(ViT) |
全量訓練LLM,凍結ViT |
LLaVA-PT (558K) |
LLaVA-Mix (665K) |
1 |
1 |
LLaVA-Llama-3-8B |
CLIP-L |
MLP |
336 |
凍結LLM,凍結ViT |
全量訓練LLM,使用低秩自適應(LoRA)訓練ViT |
LLaVA-PT (558K) |
LLaVA-Mix (665K) |
1 |
1 |
LLaVA-Llama-3-8B-v1.1 |
CLIP-L |
MLP |
336 |
凍結LLM,凍結ViT |
全量訓練LLM,使用LoRA訓練ViT |
ShareGPT4V-PT (1246K) |
InternVL-SFT (1268K) |
1 |
1 |
LLaVA-Phi-3-mini |
CLIP-L |
MLP |
336 |
凍結LLM,凍結ViT |
全量訓練LLM,全量訓練ViT |
ShareGPT4V-PT (1246K) |
InternVL-SFT (1268K) |
1 |
2 |
實驗結果
模型 |
MMBench測試(英文) |
MMMU驗證集 |
SEED-IMG |
AI2D測試 |
ScienceQA測試 |
HallusionBench準確率 |
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 |
📄 許可證
@misc{2023xtuner,
title={XTuner: A Toolkit for Efficiently Fine-tuning LLM},
author={XTuner Contributors},
howpublished = {\url{https://github.com/InternLM/xtuner}},
year={2023}
}