Add pipeline tag and paper link

#5
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -1,8 +1,9 @@
1
  ---
2
- library_name: transformers
3
- license: apache-2.0
4
  base_model:
5
  - Qwen/Qwen3.5-4B
 
 
 
6
  tags:
7
  - decision-making
8
  - multimodal
@@ -12,7 +13,7 @@ tags:
12
 
13
  # Intern-Decision-4B
14
 
15
- [Demo](https://huggingface.co/spaces/internlm/intern-decision) | [Model Weights](https://huggingface.co/collections/internlm/intern-decision) | [GitHub](https://github.com/internlm/Intern-Decision)
16
 
17
  **Intern-Decision-4B** is a multimodal structured decision model fine-tuned from
18
  **[Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)**.
@@ -226,4 +227,4 @@ Intern-Decision is derived from the Qwen3.5 series. The original Qwen license is
226
  as [LICENSE-QWEN](LICENSE-QWEN). Retain the license and applicable
227
  upstream notices when redistributing. These weights were modified by decision
228
  tuning, and this release adds the structured inference wrapper and model card.
229
- We thank the Qwen team for the original models and multimodal processor.
 
1
  ---
 
 
2
  base_model:
3
  - Qwen/Qwen3.5-4B
4
+ library_name: transformers
5
+ license: apache-2.0
6
+ pipeline_tag: image-text-to-text
7
  tags:
8
  - decision-making
9
  - multimodal
 
13
 
14
  # Intern-Decision-4B
15
 
16
+ [Paper](https://huggingface.co/papers/2610.22131) | [Demo](https://huggingface.co/spaces/internlm/intern-decision) | [Model Weights](https://huggingface.co/collections/internlm/intern-decision) | [GitHub](https://github.com/internlm/Intern-Decision)
17
 
18
  **Intern-Decision-4B** is a multimodal structured decision model fine-tuned from
19
  **[Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)**.
 
227
  as [LICENSE-QWEN](LICENSE-QWEN). Retain the license and applicable
228
  upstream notices when redistributing. These weights were modified by decision
229
  tuning, and this release adds the structured inference wrapper and model card.
230
+ We thank the Qwen team for the original models and multimodal processor.