EpistemeAI
/

metatune-gpt20b-R1

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

legolasyiu commited on Nov 3, 2025

Commit

e51e01f

·

verified ·

1 Parent(s): eb2ee31

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -96,9 +96,9 @@ This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas
 |:-----------------------|:-----|:-----|:----- |
 |gsm8k_cot               |0.91  |   -  |   -   |
 |gpqa_diamond_cot_n_shot |0.722 |      |  -    |
-|hellaswag               |0.421 | 0.525|-      |
 |arc_challenge           |0.349 | 0.349|-      |
-|winogrande              |0.7851| 0.5928|-     |

 |:-----------------------|:-----|:-----|:----- |
 |gsm8k_cot               |0.91  |   -  |   -   |
 |gpqa_diamond_cot_n_shot |0.722 |      |  -    |
+|hellaswag               |0.421 | **0.525**|-      |
 |arc_challenge           |0.349 | 0.349|-      |
+|winogrande              |**0.7851**| 0.5928|-     |