Improve model card (#1)

- Improve model card (7248878fa9db0df1f3472586406db30249486b64)


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

README.md

@@ -4,6 +4,18 @@ datasets:
 - internlm/OREAL-RL-Prompts
 base_model:
 - deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+---
+license: apache-2.0
+datasets:
+- internlm/OREAL-RL-Prompts
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+library_name: transformers
+pipeline_tag: text-generation
 ---
 
 # OREAL-DeepSeek-R1-Distill-Qwen-7B
@@ -62,11 +74,11 @@ We release not only the **RL** models, but also the **SFT** models for the **ORE
 
 | Model | Link |
 |-------|------|
-|**RL Models**||
+|**RL Models**|
 | OREAL-7B | [Hugging Face](https://huggingface.co/internlm/OREAL-7B) |
 | OREAL-DSR1-Distill-Qwen-7B | [Hugging Face](https://huggingface.co/internlm/OREAL-DeepSeek-R1-Distill-Qwen-7B) |
 | OREAL-32B | [Hugging Face](https://huggingface.co/internlm/OREAL-32B) |
-| **SFT Models** | |
+| **SFT Models** | 
 | OREAL-7B-SFT | [Hugging Face](https://huggingface.co/internlm/OREAL-7B-SFT) |
 | OREAL-32B-SFT | [Hugging Face](https://huggingface.co/internlm/OREAL-32B-SFT) |