Update README.md
Browse files
README.md
CHANGED
|
@@ -32,10 +32,6 @@ datasets:
|
|
| 32 |
>
|
| 33 |
> - ⚠️**Trade-off:** −1.24% on HumanEval+ −7.2% on MMLU-Pro (Indicating reduced general knowledge reasoning performance)
|
| 34 |
>
|
| 35 |
-
> Overall, v2 validates that models can **think shorter and smarter — not longer — while maintaining performance**.
|
| 36 |
-
>
|
| 37 |
-
> *(Detailed benchmark analysis provided below.)*
|
| 38 |
-
>
|
| 39 |
> *⚠️Note: Due to the scope of SFT data and training focus, the model may underperform the base model on certain tasks requiring long-context understanding or more complex multi-step reasoning. The efficiency and accuracy results reported here are based solely on the HumanEval and HumanEval+ benchmarks. Thank you for your understanding.*
|
| 40 |
|
| 41 |
|
|
|
|
| 32 |
>
|
| 33 |
> - ⚠️**Trade-off:** −1.24% on HumanEval+ −7.2% on MMLU-Pro (Indicating reduced general knowledge reasoning performance)
|
| 34 |
>
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
> *⚠️Note: Due to the scope of SFT data and training focus, the model may underperform the base model on certain tasks requiring long-context understanding or more complex multi-step reasoning. The efficiency and accuracy results reported here are based solely on the HumanEval and HumanEval+ benchmarks. Thank you for your understanding.*
|
| 36 |
|
| 37 |
|