Update paper link to Hugging Face Papers page (#4)

- Update paper link to Hugging Face Papers page (1edbf997c665461f30fa4d44ef27c95fd83ab0f4)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,14 +1,15 @@
 ---
-pipeline_tag: image-text-to-text
-library_name: transformers
-license: mit
-language:
-- en
 base_model:
 - OpenGVLab/InternVL3-38B
+language:
+- en
+library_name: transformers
+license: mit
+pipeline_tag: image-text-to-text
 tags:
 - Skywork R1V
 ---
+
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->
 <!-- markdownlint-disable no-duplicate-header -->
@@ -27,7 +28,7 @@ tags:
 
 
 <p align="center">
-    <a href="https://github.com/SkyworkAI/Skywork-R1V/blob/main/Skywork_R1V3.pdf"><strong>📖 R1V3 Report</strong></a> |
+    <a href="https://huggingface.co/papers/2507.06167"><strong>📖 R1V3 Report</strong></a> |
     <a href="https://github.com/SkyworkAI/Skywork-R1V"><strong>💻 GitHub</strong></a> 
   
 </p>
@@ -60,7 +61,7 @@ Skywork-R1V3 is an advanced, open-source Vision-Language Model (VLM) built on se
 
 - **Entropy of Critical Reasoning Tokens**: This unique indicator effectively gauges reasoning capability, guiding checkpoint selection during RL training.
 
-These innovations lead to Broad Reasoning Generalization, allowing our RL-powered approach to successfully extend mathematical reasoning to diverse subject areas. Additionally, our work delves into RL-specific explorations like curriculum learning and learning rate strategies, alongside a broader discussion on multimodal reasoning. For more details, refer to our [[📖 R1V3 Report](https://github.com/SkyworkAI/Skywork-R1V/blob/main/Skywork_R1V3.pdf)] .
+These innovations lead to Broad Reasoning Generalization, allowing our RL-powered approach to successfully extend mathematical reasoning to diverse subject areas. Additionally, our work delves into RL-specific explorations like curriculum learning and learning rate strategies, alongside a broader discussion on multimodal reasoning. For more details, refer to our [[📖 R1V3 Report](https://huggingface.co/papers/2507.06167)] .
 ## 3. Evaluation
 
 ### 🌟 Key Results
@@ -140,11 +141,13 @@ def main():
         pixel_values = pixel_values[0]
         num_patches_list = None
         
-    prompt = "<image>\n"*len(args.image_paths) + args.question
+    prompt = "<image>
+"*len(args.image_paths) + args.question
     generation_config = dict(max_new_tokens=64000, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.05)
     response = model.chat(tokenizer, pixel_values, prompt, generation_config, num_patches_list=num_patches_list)
 
-    print(f'User: {args.question}\nAssistant: {response}')
+    print(f'User: {args.question}
+Assistant: {response}')
 
 if __name__ == '__main__':
     main()