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:
- CLIP-like ViT-H/14
- 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
| Model | LLM Size | SQA | MME | MMBench | Average¹ |
|---|---|---|---|---|---|
| UForm-Gen2-Qwen-500m | 0.5B | 45.5 | 880.1 | 42.0 | 29.31 |
| MobileVLM v2 | 1.4B | 52.1 | 1302.8 | 57.7 | 36.81 |
| LLaVA-Phi | 2.7B | 68.4 | 1335.1 | 59.8 | 42.95 |
¹MME scores were divided by 2000 before averaging.