EpistemeAI
/

metatune-gpt20b-R1

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

legolasyiu commited on 3 days ago

Commit

cde18e7

·

verified ·

1 Parent(s): e51e01f

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -94,9 +94,9 @@ This smaller model `gpt-oss-20b` can be fine-tuned on consumer hardware, whereas
 |             Tasks      |metatune R0|metatune R1|Llama 4 Maverick|
 |:-----------------------|:-----|:-----|:----- |
-|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|-     |

 |             Tasks      |metatune R0|metatune R1|Llama 4 Maverick|
 |:-----------------------|:-----|:-----|:----- |
+|gsm8k_cot               |0.91  |0.9796|   -   |
 |gpqa_diamond_cot_n_shot |0.722 |      |  -    |
+|hellaswag               |0.421 |**0.525**|-      |
 |arc_challenge           |0.349 | 0.349|-      |
 |winogrande              |**0.7851**| 0.5928|-     |