PursuitOfDataScience
/

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

Model card Files Files and versions

PursuitOfDataScience commited on Mar 22, 2025

Commit

eb5757b

·

verified ·

1 Parent(s): 72d89a9

Update README.md

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -33,14 +33,13 @@ After following the sampling-based Pass@1 methodology inspired by [DeepSeek R1](
 | Parameter        | Value   |
 |------------------|---------|
-| **Dataset**      | `uggingFaceH4/MATH-500` |
 | **Temperature**  | `0.6`   |
 | **Top_p**        | `0.95`  |
 | **Num_samples**  | `16` per question |
-### Results
-- **At-least-one-correct Rate:** **54.60%** (273 out of 500 questions)
 *This metric represents the percentage of questions with at least one correct solution among multiple generated attempts.*

 | Parameter        | Value   |
 |------------------|---------|
+| **Dataset**      | `HuggingFaceH4/MATH-500` |
 | **Temperature**  | `0.6`   |
 | **Top_p**        | `0.95`  |
 | **Num_samples**  | `16` per question |
+**At-least-one-correct Rate:** **54.60%** (273 out of 500 questions)
 *This metric represents the percentage of questions with at least one correct solution among multiple generated attempts.*