PursuitOfDataScience
/

Qwen2.5-1.5B-Instruct-Lora-Deepseek-R1

Model card Files Files and versions

PursuitOfDataScience commited on Mar 22

Commit

64d3d2a

·

verified ·

1 Parent(s): eb5757b

Update README.md

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -33,9 +33,10 @@ After following the sampling-based Pass@1 methodology inspired by [DeepSeek R1](
 | Parameter        | Value   |
 |------------------|---------|
-| **Dataset**      | `HuggingFaceH4/MATH-500` |
-| **Temperature**  | `0.6`   |
-| **Top_p**        | `0.95`  |
 | **Num_samples**  | `16` per question |

 | Parameter        | Value   |
 |------------------|---------|
+| **dataset**      | `HuggingFaceH4/MATH-500` |
+| **temperature**  | `0.6`   |
+| **top_p**        | `0.95`  |
+| **max_new_tokens** |  2048   |
 | **Num_samples**  | `16` per question |