datasets:
- liuhaotian/LLaVA-Pretrain
- liuhaotian/LLaVA-Instruct-150K
language:
- en
tags:
- llava
- phi
license: mit
library_name: transformers
widget:
- text: What animal is it?
src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
- text: Where is it?
src: >-
https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
Multi-crop LLaVA-3b
Model details
The core idea behind multi-crop LLaVA (MC-LLaVA) is that instead of N visual token embeddings per image, I generate one token embedding per N parts of the image. Having high-quality embeddings for smaller parts of the image helps to extract more details and understand the scene better.
For every crop of the image, I generate an embedding from the full SigLIP encoder (size [1, 1152]) and then push all N embeddings through the LLaVA adapter, which gives the token embedding of size [N, 2560]. Right now, the tokens do not contain explicit information about their position in the original image. I plan to add it later.
MC-LLaVA-3b was fine-tuned from Dolphin 2.6 Phi using vision tower from SigLIP 400M.
The context length during training was 1200 tokens, as the L4 GPUs I used didn't allow me to get more.
As Dolphin 2.6 Phi, LLaVA-3b uses ChatML prompt format:
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
How to use
Install dependencies
!pip install -q open_clip_torch timm einops
Download modeling files
from huggingface_hub import hf_hub_download
hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="configuration_llava.py", local_dir="./", force_download=True)
hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="configuration_phi.py", local_dir="./", force_download=True)
hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="modeling_llava.py", local_dir="./", force_download=True)
hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="modeling_phi.py", local_dir="./", force_download=True)
hf_hub_download(repo_id="OEvortex/HelpingAI-Vision", filename="processing_llava.py", local_dir="./", force_download=True)
Create a model
from modeling_llava import LlavaForConditionalGeneration
import torch
model = LlavaForConditionalGeneration.from_pretrained("OEvortex/HelpingAI-Vision", torch_dtype=torch.float16)
model = model.to("cuda")
Create processors
from transformers import AutoTokenizer
from processing_llava import LlavaProcessor, OpenCLIPImageProcessor
tokenizer = AutoTokenizer.from_pretrained("OEvortex/HelpingAI-Vision")
image_processor = OpenCLIPImageProcessor(model.config.preprocess_config)
processor = LlavaProcessor(image_processor, tokenizer)
Set image and text
from PIL import Image
import requests
image_file = "https://images.unsplash.com/photo-1439246854758-f686a415d9da"
raw_image = Image.open(requests.get(image_file, stream=True).raw)
prompt = """<|im_start|>system
A chat between a curious human and an artificial intelligence assistant.
The assistant gives helpful, detailed, and polite answers to the human's questions.
The assistant does not hallucinate and pays very close attention to the details.<|im_end|>
<|im_start|>user
<image>
Describe the image.<|im_end|>
<|im_start|>assistant
"""
Process inputs
inputs = processor(prompt, raw_image, model, return_tensors='pt')
inputs['input_ids'] = inputs['input_ids'].to(model.device)
inputs['attention_mask'] = inputs['attention_mask'].to(model.device)
Generate the data
import torch
with torch.inference_mode():
output = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.4, pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id)