Views
No views yet
1
2slices:
3 - sources:
4 - model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
5 layer_range: [0, 32]
6 - model: NeuralNovel/Gecko-7B-v0.1-DPO
7 layer_range: [0, 32]
8merge_method: slerp
9base_model: NeuralNovel/Mistral-7B-Instruct-v0.2-Neural-Story
10parameters:
11 t:
12 - filter: self_attn
13 value: [0, 0.5, 0.3, 0.7, 1]
14 - filter: mlp
15 value: [1, 0.5, 0.7, 0.3, 0]
16 - value: 0.5
17dtype: bfloat16
18
19
20| Metric | Value |
|---|---|
| Avg. | 65.02 |
| AI2 Reasoning Challenge (25-Shot) | 59.98 |
| HellaSwag (10-Shot) | 83.21 |
| MMLU (5-Shot) | 61.42 |
| TruthfulQA (0-shot) | 61.03 |
| Winogrande (5-shot) | 77.66 |
| GSM8k (5-shot) | 46.78 |