uform-gen2-qwen

Pocket-Sized Multimodal AI For Content Understanding and Generation

Description

UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. The model consists of two parts:

1. CLIP-like ViT-H/14
2. Qwen1.5-0.5B-Chat

The model was pre-trained on the internal image captioning dataset and fine-tuned on public instructions datasets: SVIT, LVIS, VQAs datasets. The model took one day to train on a DGX-H100 with 8x H100 GPUs. Thanks to Nebius.ai for providing the compute 🤗

Usage

The generative model can be used to caption images, answer questions about them. Also it is suitable for a multimodal chat.

from transformers import AutoModel, AutoProcessor

model = AutoModel.from_pretrained("unum-cloud/uform-gen2-qwen-500m", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("unum-cloud/uform-gen2-qwen-500m", trust_remote_code=True)

prompt = "Question or Instruction"
image = Image.open("image.jpg")

inputs = processor(text=[prompt], images=[image], return_tensors="pt")
with torch.inference_mode():
     output = model.generate(
        **inputs,
        do_sample=False,
        use_cache=True,
        max_new_tokens=256,
        eos_token_id=151645,
        pad_token_id=processor.tokenizer.pad_token_id
    )

prompt_len = inputs["input_ids"].shape[1]
decoded_text = processor.batch_decode(output[:, prompt_len:])[0]

You can check examples of different prompts in our demo space.

Evaluation

¹MME scores were divided by 2000 before averaging.