yinjiewang commited on
Commit
2e52630
·
verified ·
1 Parent(s): eacc33c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -1
README.md CHANGED
@@ -16,7 +16,6 @@ We introduce **ReasonFlux-Coders**, trained with **CURE**, our algorithm for co-
16
  * **ReasonFlux-Coder-7B** and **ReasonFlux-Coder-14B** outperform similarly sized Qwen Coders, DeepSeek Coders, and Seed-Coders, and naturally integrate into common test-time scaling and agentic coding pipelines.
17
  * **ReasonFlux-Coder-4B** is our Long-CoT model, outperforming Qwen3-4B while achieving 64.8% efficiency in unit test generation. We have demonstrated its ability to serve as a reward model for training base models via reinforcement learning (see our [paper](https://arxiv.org/abs/2505.15809)).
18
 
19
-
20
  [Paper](https://arxiv.org/abs/2505.15809) | [Code](https://github.com/Gen-Verse/CURE)
21
 
22
  # Citation
 
16
  * **ReasonFlux-Coder-7B** and **ReasonFlux-Coder-14B** outperform similarly sized Qwen Coders, DeepSeek Coders, and Seed-Coders, and naturally integrate into common test-time scaling and agentic coding pipelines.
17
  * **ReasonFlux-Coder-4B** is our Long-CoT model, outperforming Qwen3-4B while achieving 64.8% efficiency in unit test generation. We have demonstrated its ability to serve as a reward model for training base models via reinforcement learning (see our [paper](https://arxiv.org/abs/2505.15809)).
18
 
 
19
  [Paper](https://arxiv.org/abs/2505.15809) | [Code](https://github.com/Gen-Verse/CURE)
20
 
21
  # Citation