Views
No views yet
1
2slices:
3 - sources:
4 - model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
5 layer_range: [0, 32]
6 - model: microsoft/Phi-3.5-mini-instruct
7 layer_range: [0, 32]
8merge_method: slerp
9base_model: jpacifico/Chocolatine-3B-Instruct-DPO-Revised
10parameters:
11 t:
12 - filter: self_attn
13 value: [0, 0.25, 0.5, 0.75, 1]
14 - filter: mlp
15 value: [1, 0.75, 0.5, 0.25, 0]
16 - value: 0.5
17dtype: bfloat16
18
19| Metric | Value |
|---|---|
| Avg. | 21.88 |
| IFEval (0-Shot) | 27.22 |
| BBH (3-Shot) | 35.70 |
| MATH Lvl 5 (4-Shot) | 8.91 |
| GPQA (0-shot) | 9.28 |
| MuSR (0-shot) | 18.22 |
| MMLU-PRO (5-shot) | 31.96 |