Views
No views yet
DARE_TIES merge method.1base_model: mistralai/Mistral-7B-v0.1
2dtype: bfloat16
3merge_method: dare_ties
4models:
5- model: mistralai/Mistral-7B-v0.1
6- model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
7 parameters:
8 density: 0.8
9 weight: 0.3
10- model: Q-bert/MetaMath-Cybertron-Starling
11 parameters:
12 density: 0.8
13 weight: 0.3
14- model: ise-uiuc/Magicoder-S-CL-7B
15 parameters:
16 density: 0.6
17 weight: 0.2
18- model: AIDC-ai-business/Marcoroni-7B-v3
19 parameters:
20 density: 0.6
21 weight: 0.2
22parameters:
23 int8_mask: true1337 with OpenAI compatible endpoints
| Metric | Value |
|---|---|
| Avg. | ? |
| ARC (25-shot) | ? |
| HellaSwag (10-shot) | ? |
| MMLU (5-shot) | ? |
| TruthfulQA (0-shot) | ? |
| Winogrande (5-shot) | ? |
| GSM8K (5-shot) | ? |
| Metric | Value |
|---|---|
| Avg. | 29.49 |
| AI2 Reasoning Challenge (25-Shot) | 27.73 |
| HellaSwag (10-Shot) | 25.83 |
| MMLU (5-Shot) | 27.04 |
| TruthfulQA (0-shot) | 47.27 |
| Winogrande (5-shot) | 49.09 |
| GSM8k (5-shot) | 0.00 |