Add link to paper

README.md

@@ -1,15 +1,15 @@
 ---
-library_name: transformers
-license: apache-2.0
+base_model:
+- HuggingFaceTB/SmolLM2-360M-Instruct
+- google/siglip-base-patch16-512
 datasets:
 - HuggingFaceM4/the_cauldron
 - HuggingFaceM4/Docmatix
-pipeline_tag: image-text-to-text
 language:
 - en
-base_model:
-- HuggingFaceTB/SmolLM2-360M-Instruct
-- google/siglip-base-patch16-512
+library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
 ---
 
 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/SmolVLM_256_banner.png" width="800" height="auto" alt="Image description">
@@ -30,6 +30,7 @@ SmolVLM-500M is a tiny multimodal model, member of the SmolVLM family. It accept
 
 - **Demo:** [SmolVLM-256 Demo](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM-256M-Demo)
 - **Blog:** [Blog post](https://huggingface.co/blog/smolvlm)
+- **Paper:** [](https://huggingface.co/papers/2504.05299)
 
 ## Uses
 
@@ -39,10 +40,8 @@ To fine-tune SmolVLM on a specific task, you can follow [the fine-tuning tutoria
 
 ## Evaluation
 
-
 <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/smoller_vlm_benchmarks.png" alt="Benchmarks" style="width:90%;" />
 
-
 ### Technical Summary
 
 SmolVLM leverages the lightweight SmolLM2 language model to provide a compact yet powerful multimodal experience. It introduces several changes compared to the larger SmolVLM 2.2B model:
@@ -112,7 +111,6 @@ In summary, the image showcases the Statue of Liberty, a symbol of freedom and d
 """
 ```
 
-
 ### Model optimizations
 
 **Precision**: For better performance, load and run the model in half-precision (`torch.bfloat16`) if your hardware supports it.
@@ -143,7 +141,6 @@ model = AutoModelForVision2Seq.from_pretrained(
 **Vision Encoder Efficiency**: Adjust the image resolution by setting `size={"longest_edge": N*512}` when initializing the processor, where N is your desired value. The default `N=4` works well, which results in input images of
 size 2048×2048. Decreasing N can save GPU memory and is appropriate for lower-resolution images. This is also useful if you want to fine-tune on videos.
 
-
 ## Misuse and Out-of-scope Use
 
 SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to:
@@ -180,5 +177,4 @@ You can cite us in the following way:
   journal={arXiv preprint arXiv:2504.05299},
   year={2025}
 }
-```
-
+```