azzzacs commited on
Commit
289a41e
·
verified ·
1 Parent(s): 20de96f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -8,6 +8,10 @@ tags:
8
  - code
9
  ---
10
 
 
 
 
 
11
  # LogicCoder-7B
12
 
13
  **LogicCoder-7B** is a 7B-parameter language model fine-tuned for code generation tasks. It is based on the DeepSeek-R1-Distill-Qwen-7B model and trained on a Python subset of the open-r1/codeforces-cots dataset.
 
8
  - code
9
  ---
10
 
11
+ # Paper Page
12
+
13
+ [**Pruning the Unsurprising: Efficient Code Reasoning via First-Token Surprisal.**](https://arxiv.org/abs/2508.05988)
14
+
15
  # LogicCoder-7B
16
 
17
  **LogicCoder-7B** is a 7B-parameter language model fine-tuned for code generation tasks. It is based on the DeepSeek-R1-Distill-Qwen-7B model and trained on a Python subset of the open-r1/codeforces-cots dataset.