Add library_name, paper link, and sample usage (#1)

- Add library_name, paper link, and sample usage (47914ca3385b190985b65860221cd365cef9d430)


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

README.md

@@ -1,15 +1,89 @@
 ---
-language:
-- en
 base_model:
 - kyutai/helium-1-2b
-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 `Helium1-VL-2B`, a Helium1-2B model which is instruct-tuned and further trained to handle visual inputs using a pretrained encoder from Qwen-2.5VL.
-This model is released as part of our CASA model release. We provide model weights for CASA models in the associated model collection.
+# Helium1-VL-2B
+
+`Helium1-VL-2B` is an instruct-tuned vision-language model (VLM) based on the [Helium1-2B](https://huggingface.co/kyutai/helium-1-2b) text-only language model and a pretrained vision encoder from [Qwen-2.5VL](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
+
+This model is released as part of the **CASA** project. While the CASA architecture focuses on cross-attention fusion, `Helium1-VL-2B` serves as a high-performance **token insertion** baseline, achieving state-of-the-art results among models of comparable size trained on publicly available datasets.
+
+- **Paper:** [CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion](https://huggingface.co/papers/2512.19535)
+- **Project Page:** [https://kyutai.org/casa](https://kyutai.org/casa)
+- **GitHub Repository:** [https://github.com/kyutai-labs/casa](https://github.com/kyutai-labs/casa)
+
+## Sample Usage
+
+You can run inference using the following code snippet. This model requires `trust_remote_code=True` to load the custom architecture.
+
+```python
+import torch
+from transformers.models.auto.modeling_auto import AutoModel
+from transformers.models.auto.processing_auto import AutoProcessor
+
+model_id = "kyutai/Helium1-VL-2B"
+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
+
+If you use this model or the CASA fusion paradigm in your research, please cite:
+
+```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}
+}
+```