peakji
/

peak-reasoning-7b-awq

4-bit precision

Model card Files Files and versions Community

peakji commited on 15 days ago

Commit

bc61712

•

1 Parent(s): e7c687a

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -11,4 +11,4 @@ base_model:
 - peakji/peak-reasoning-7b
 ---
-⚠️DEPRECATED: Please switch to the [Steiner-preview](https://huggingface.co/peakji/steiner-32b-preview-awq) series models, which are trained using reinforcement learning with step-level rewards on backtrack-able synthetic datasets.

 - peakji/peak-reasoning-7b
 ---
+⚠️DEPRECATED: Please switch to the [Steiner-preview](https://huggingface.co/peakji/steiner-32b-preview-awq) series models, which are trained with reinforcement learning and backtrack-able synthetic datasets.