The CleverBoi series is based on models that have been fine tuned on a collection of data sets that emphasize logic, inference, math and coding, also known as the CleverBoi data set.
This model has been fine tuned for 1 epoch on the CleverBoi-Data-20k data set.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 14.01 |
| IFEval (0-Shot) | 19.61 |
| BBH (3-Shot) | 24.13 |
| MATH Lvl 5 (4-Shot) | 4.46 |
| GPQA (0-shot) | 4.81 |
| MuSR (0-shot) | 6.72 |
| MMLU-PRO (5-shot) | 24.31 |
