CASA-Qwen2_5-VL-3B
This repository contains the model weights for CASA-Qwen2_5-VL-3B, introduced in the paper CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion.
This model is a Qwen-2.5VL-3B-Instruct model adapted from token insertion to a cross-attention-based architecture.
- Paper: CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion
- Project Page: kyutai.org/casa
- Code: github.com/kyutai-labs/casa
Sample Usage
This model requires trust_remote_code=True to load the custom architecture. Below is a snippet to run inference using transformers.
import torch
from transformers.models.auto.modeling_auto import AutoModel
from transformers.models.auto.processing_auto import AutoProcessor
model_id = "kyutai/CASA-Qwen2_5-VL-3B"
model = AutoModel.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
attn_implementation="flash_attention_2",
trust_remote_code=True,
).cuda()
processor = AutoProcessor.from_pretrained(
model_id,
trust_remote_code=True,
)
conversation = [
{
"role": "user",
"content": [
{
"type": "image",
"image": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.png",
},
{
"type": "text",
"text": "Describe this image.",
},
],
},
]
inputs = processor.tokenize_messages(messages=conversation)
inputs = inputs.to(model.device)
input_len = inputs["input_ids"].shape[1]
output_ids = model.generate_from_image(
**inputs,
max_new_tokens=512,
pre_image_tokens=processor.pre_image_tokens,
post_image_tokens=processor.post_image_tokens,
eos_token_id=model.generation_config.eos_token_id,
)[0, input_len:]
response = processor.tokenizer.decode(output_ids, skip_special_tokens=True)
print(response)
Citation
@article{kyutai2025casa,
author = {Moritz B\"ohle and Am\'elie Royer and Juliette Marrie and Edouard Grave and Patrick P\'erez},
year = {2025},
title = {CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion},
journal = {ArXiv},
url = {https://arxiv.org/abs/2512.19535}
}
License
The code in the official repository is provided under the MIT license. The weights for this model are released under the CC-BY-NC-SA 4.0 license. Additionally, as this model includes weights from Qwen2.5-VL-3B, it is subject to the Qwen RESEARCH LICENSE AGREEMENT.