Views
No views yet
1
2slices:
3 - sources:
4 - model: bagel-dpo-34b-v0.2
5 layer_range: [0, 60]
6 - model: Nous-Hermes-2-Yi-34B
7 layer_range: [0, 60]
8
9merge_method: slerp
10base_model: nontoxic-bagel-34b-v0.2
11
12parameters:
13 t:
14 - filter: self_attn
15 value: [0, 0.5, 0.3, 0.7, 1]
16 - filter: mlp
17 value: [1, 0.5, 0.7, 0.3, 0]
18 - value: 0.5
19tokenizer_source: union
20dtype: bfloat16
21| Metric | Value |
|---|---|
| Avg. | 75.24 |
| AI2 Reasoning Challenge (25-Shot) | 70.73 |
| HellaSwag (10-Shot) | 85.68 |
| MMLU (5-Shot) | 77.29 |
| TruthfulQA (0-shot) | 67.09 |
| Winogrande (5-shot) | 84.37 |
| GSM8k (5-shot) | 66.26 |
| Metric | Value |
|---|---|
| Avg. | 27.06 |
| IFEval (0-Shot) | 46.03 |
| BBH (3-Shot) | 41.96 |
| MATH Lvl 5 (4-Shot) | 4.91 |
| GPQA (0-shot) | 11.30 |
| MuSR (0-shot) | 17.01 |
| MMLU-PRO (5-shot) | 41.15 |