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

UForm Vision Encoder
Sheared-LLaMA-1.3B manually tuned on the instructions dataset

The model was pre-trained on: MSCOCO, SBU Captions, Visual Genome, VQAv2, GQA and a few internal datasets. UForm-Gen-Chat is SFT version of UForm-Gen for multimodal chat.

Usage

pip install uform

For the CLI demo run the following:

bash

uform-chat --model unum-cloud/uform-gen-chat --image_path=zebra.jpg
uform-chat --model unum-cloud/uform-gen-chat --image_path=zebra.jpg --device="cuda:0" --fp16

Or if you want to use the model in your code:

python

from uform.gen_model import VLMForCausalLM, VLMProcessor

model = VLMForCausalLM.from_pretrained("unum-cloud/uform-gen-chat")
processor = VLMProcessor.from_pretrained("unum-cloud/uform-gen-chat")

prompt = "What do you see?"
image = Image.open("zebra.jpg")

inputs = processor(texts=[prompt], images=[image], return_tensors="pt")
with torch.inference_mode():
     output = model.generate(
        **inputs,
        do_sample=False,
        use_cache=True,
        max_new_tokens=128,
        eos_token_id=32001,
        pad_token_id=processor.tokenizer.pad_token_id
    )

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

Evaluation

For captioning evaluation we measure CLIPScore and RefCLIPScore¹.

Model	Size	Caption Length	CLIPScore	RefCLIPScore
`llava-hf/llava-1.5-7b-hf`	7B	Long	0.878	0.529
`llava-hf/llava-1.5-7b-hf`	7B	Short	0.886	0.531

`Salesforce/instructblip-vicuna-7b`	7B	Long	0.902	0.534
`Salesforce/instructblip-vicuna-7b`	7B	Short	0.848	0.523

`unum-cloud/uform-gen-chat`	1.5B	Long	0.860	0.525
`unum-cloud/uform-gen-chat`	1.5B	Short	0.858	0.525

¹ We used apple/DFN5B-CLIP-ViT-H-14-378 CLIP model.

unum-cloud/uform-gen-chat

UForm

Pocket-Sized Multimodal AI For Content Understanding and Generation

Description

Usage

Evaluation

unum-cloud/
uform-gen-chat

Pocket-Sized Multimodal AI
For Content Understanding and Generation