Slerp Merge of Mistral-7B-Instruct-v0.2 and cookinai/CatMacaroni-Slerp
.yaml file for mergekit
slices:
- sources:
- model: Mistral-7B-Instruct-v0.2
layer_range: [0, 32]
- model: CatMacaroni-Slerp-7B
layer_range: [0, 32]
merge_method: slerp
base_model: Mistral-7B-Instruct-v0.2
parameters:
t:
- value: [0, 0.3, 0.5, 0.7, 1]
dtype: float16
| Metric | Value |
|---|---|
| Avg. | 69.08 |
| ARC (25-shot) | 65.53 |
| HellaSwag (10-shot) | 85.66 |
| MMLU (5-shot) | 61.53 |
| TruthfulQA (0-shot) | 64.1 |
| Winogrande (5-shot) | 80.03 |
| GSM8K (5-shot) | 57.62 |
- Downloads last month
- 120