Views
No views yet

base_model: ./maldv/spring
gate_mode: hidden
dtype: bfloat16
experts_per_token: 2
experts:
- source_model: ./models/Llama3-ChatQA-1.5-8B
positive_prompts:
- 'add numbers'
- 'solve for x'
negative_prompts:
- 'I love you'
- 'Help me'
- source_model: ./models/InfinityRP-v2-8B
positive_prompts:
- 'they said'
- source_model: ./models/Einstein-v6.1-Llama3-8B
positive_prompts:
- 'the speed of light'
- 'chemical reaction'
- source_model: ./models/Llama-3-Soliloquy-8B-v2
positive_prompts:
- 'write a'
- source_model: ./models/Llama-3-Lumimaid-8B-v0.1
positive_prompts:
- 'she looked'
- source_model: ./models/L3-TheSpice-8b-v0.8.3
positive_prompts:
- 'they felt'
- source_model: ./models/Llama3-OpenBioLLM-8B
positive_prompts:
- 'the correct treatment'
- source_model: ./models/Llama-3-SauerkrautLM-8b-Instruct
positive_prompts:
- 'help me'
- 'should i'1[
2 'Einstein-v6.1-Llama3-8B',
3 'L3-TheSpice-8b-v0.8.3',
4 'Configurable-Hermes-2-Pro-Llama-3-8B',
5 'Llama3-ChatQA-1.5-8B',
6 'Llama3-OpenBioLLM-8B',
7 'InfinityRP-v2-8B',
8 'Llama-3-Soliloquy-8B-v2',
9 'Tiamat-8b-1.2-Llama-3-DPO',
10 'Llama-3-8B-Instruct-Gradient-1048k',
11 'Llama-3-Lumimaid-8B-v0.1',
12 'Llama-3-SauerkrautLM-8b-Instruct',
13 'Meta-Llama-3-8B-Instruct-DPO',
14]| Metric | Score |
|---|---|
| Average | 65.89 |
| ARC | 63.05 |
| HellaSwag | 82.49 |
| MMLU | 64.45 |
| TruthfulQA | 51.63 |
| Winogrande | 76.24 |
| GSM8K | 51.63 |