Views
No views yet
1slices:
2- sources:
3 - model: princeton-nlp/Llama-3-Instruct-8B-SimPO
4 layer_range:
5 - 0
6 - 32
7 - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
8 layer_range:
9 - 0
10 - 32
11merge_method: slerp
12base_model: princeton-nlp/Llama-3-Instruct-8B-SimPO
13parameters:
14 t:
15 - filter: self_attn
16 value:
17 - 0
18 - 0.5
19 - 0.3
20 - 0.7
21 - 1
22 - filter: mlp
23 value:
24 - 1
25 - 0.5
26 - 0.7
27 - 0.3
28 - 0
29 - value: 0.5
30dtype: bfloat16
31| Metric | Value |
|---|---|
| Avg. | 23.59 |
| IFEval (0-Shot) | 68.06 |
| BBH (3-Shot) | 29.07 |
| MATH Lvl 5 (4-Shot) | 6.19 |
| GPQA (0-shot) | 1.68 |
| MuSR (0-shot) | 6.70 |
| MMLU-PRO (5-shot) | 29.83 |