Improve model card: add library name, links, and sample usage (#1)

- Improve model card: add library name, links, and sample usage (763aa63d7bf2b72f564feabdbe2c23bb33bfc452)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,14 +1,92 @@
 ---
-language:
-- en
 base_model:
 - Qwen/Qwen2.5-VL-3B-Instruct
-pipeline_tag: image-text-to-text
-license: cc-by-nc-sa-4.0
 datasets:
 - HuggingFaceM4/FineVision
 - mvp-lab/LLaVA-OneVision-1.5-Instruct-Data
+language:
+- en
+license: cc-by-nc-sa-4.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
-Please refer to the [main model card](https://huggingface.co/kyutai/CASA-Helium1-VL-2B) for more information and instructions to run.
 
-This model page contains model weights for `CASA-Qwen2_5-VL-3B`, a Qwen-2.5VL model adapted from token insertion to cross-attention based using CASA layers. We provide model weights for other CASA models in the associated model collection.
+# CASA-Qwen2_5-VL-3B
+
+This repository contains the model weights for **CASA-Qwen2_5-VL-3B**, introduced in the paper [CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion](https://huggingface.co/papers/2512.19535).
+
+CASA is a vision-language fusion paradigm that improves on cross-attention while preserving its scalability. This model is a [Qwen-2.5VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) model adapted from token insertion to a cross-attention-based architecture using CASA layers.
+
+- **Paper:** [CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion](https://arxiv.org/abs/2512.19535)
+- **Project Page:** [kyutai.org/casa](https://kyutai.org/casa)
+- **Code:** [github.com/kyutai-labs/casa](https://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`.
+
+```python
+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
+
+```bibtex
+@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 via 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](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE).