nielsr HF staff commited on
Commit
737d30f
·
verified ·
1 Parent(s): 1232652

Add pipeline tag, link to paper

Browse files

This PR adds the pipeline tag, ensuring the model can be found at https://huggingface.co./models?pipeline_tag=text-generation.
It also links to the paper page.

Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -1,12 +1,16 @@
1
  ---
2
  license: mit
3
  library_name: transformers
 
4
  ---
 
5
  # DeepSeek-R1
6
  <!-- markdownlint-disable first-line-h1 -->
7
  <!-- markdownlint-disable html -->
8
  <!-- markdownlint-disable no-duplicate-header -->
9
 
 
 
10
  <div align="center">
11
  <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
12
  </div>
@@ -46,7 +50,7 @@ library_name: transformers
46
 
47
 
48
  <p align="center">
49
- <a href="https://github.com/deepseek-ai/DeepSeek-R1/blob/main/DeepSeek_R1.pdf"><b>Paper Link</b>👁️</a>
50
  </p>
51
 
52
 
@@ -234,4 +238,4 @@ DeepSeek-R1 series support commercial use, allow for any modifications and deriv
234
  ```
235
 
236
  ## 9. Contact
237
- If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).
 
1
  ---
2
  license: mit
3
  library_name: transformers
4
+ pipeline_tag: text-generation
5
  ---
6
+
7
  # DeepSeek-R1
8
  <!-- markdownlint-disable first-line-h1 -->
9
  <!-- markdownlint-disable html -->
10
  <!-- markdownlint-disable no-duplicate-header -->
11
 
12
+ This repository contains the model described in the paper [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://huggingface.co/papers/2501.12948).
13
+
14
  <div align="center">
15
  <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V3" />
16
  </div>
 
50
 
51
 
52
  <p align="center">
53
+ <a href="https://huggingface.co/papers/2501.12948"><b>Paper Link</b>👁️</a>
54
  </p>
55
 
56
 
 
238
  ```
239
 
240
  ## 9. Contact
241
+ If you have any questions, please raise an issue or contact us at [[email protected]]([email protected]).