The LLaVA-OneVision models are 0.5/7/72B parameter models trained on LLaVA-OneVision, based on Qwen2 language model with a context window of 32K tokens.

Repository: LLaVA-VL/LLaVA-NeXT
Project Website: llava-onevision.lmms-lab.com
Paper: LLaVA-OneVision
Point of Contact: Bo Li
Languages: English, Chinese

Use

Intended use

The model was trained on LLaVA-OneVision Dataset and have the ability to interact with images, multi-image and videos.

Feel free to share your generations in the Community tab!

Generation

We provide the simple generation process for using our model. For more details, you could refer to Github.

python

# pip install git+https://github.com/LLaVA-VL/LLaVA-NeXT.git
from llava.model.builder import load_pretrained_model
from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token
from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX
from llava.conversation import conv_templates, SeparatorStyle

from PIL import Image
import requests
import copy
import torch

import sys
import warnings

warnings.filterwarnings("ignore")
pretrained = "lmms-lab/llava-onevision-qwen2-0.5b-ov"
model_name = "llava_qwen"
device = "cuda"
device_map = "auto"
tokenizer, model, image_processor, max_length = load_pretrained_model(pretrained, None, model_name, device_map=device_map)  # Add any other thing you want to pass in llava_model_args

model.eval()

url = "https://github.com/haotian-liu/LLaVA/blob/1a91fc274d7c35a9b50b3cb29c4247ae5837ce39/images/llava_v1_5_radar.jpg?raw=true"
image = Image.open(requests.get(url, stream=True).raw)
image_tensor = process_images([image], image_processor, model.config)
image_tensor = [_image.to(dtype=torch.float16, device=device) for _image in image_tensor]

conv_template = "qwen_1_5"  # Make sure you use correct chat template for different models
question = DEFAULT_IMAGE_TOKEN + "\nWhat is shown in this image?"
conv = copy.deepcopy(conv_templates[conv_template])
conv.append_message(conv.roles[0], question)
conv.append_message(conv.roles[1], None)
prompt_question = conv.get_prompt()

input_ids = tokenizer_image_token(prompt_question, tokenizer, IMAGE_TOKEN_INDEX, return_tensors="pt").unsqueeze(0).to(device)
image_sizes = [image.size]


cont = model.generate(
    input_ids,
    images=image_tensor,
    image_sizes=image_sizes,
    do_sample=False,
    temperature=0,
    max_new_tokens=4096,
)
text_outputs = tokenizer.batch_decode(cont, skip_special_tokens=True)
print(text_outputs)

Training

Model

Architecture: SO400M + Qwen2
Pretraining Stage: LCS-558K, 1 epoch, projector
Mid Stage: A mixture of 4.7M high-quality synthetic data, 1 epoch, full model
Final-Image Stage: A mixture of 3.6M single-image data, 1 epoch, full model
OneVision Stage: A mixture of 1.6M single-image/multi-image/video data, 1 epoch, full model
Precision: bfloat16

Hardware & Software

GPUs: 256 * Nvidia Tesla A100 (for whole model series training)
Orchestration: Huggingface Trainer
Neural networks: PyTorch

Citation

@article{li2024llavaonevision,
      title={LLaVA-OneVision}, 
}

lmms-lab/llava-onevision-qwen2-0.5b-ov

LLaVA-OneVision

Table of Contents

Model Summary

Use