Views
No views yet
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>Human: {user}
### Assistant: {asistant}Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{system}
{instruction}
### Response:{system}
USER: {instruction}
ASSISTANT: 1base_model: nontoxic-bagel-34b-v0.2
2gate_mode: hidden
3dtype: bfloat16
4
5experts:
6 - source_model: bagel-dpo-34b-v0.2
7 positive_prompts: ["question answering", "Q:", science", "biology", "chemistry", "physics"]
8 negative_prompts: ["math", "reason", "mathematics", "solve", "count", "code", "python", "javascript", "programming", "algorithm"]
9
10 - source_model: Nous-Hermes-2-Yi-34B
11 positive_prompts: ["chat", "math", "reason", "mathematics", "solve", "count", "python", "javascript", "programming", "algorithm", "tell me", "assistant"]
12
13 - source_model: SUS-Chat-34B
14 positive_prompts: ["math", "reason", "mathematics", "solve", "count", "assistant"]
15
16 - source_model: platypus-yi-34b
17 positive_prompts: [""]
18 negative_prompts: ["math", "reason", "mathematics", "solve", "count"]| Metric | Value |
|---|---|
| Avg. | 75.48 |
| AI2 Reasoning Challenge (25-Shot) | 69.71 |
| HellaSwag (10-Shot) | 85.28 |
| MMLU (5-Shot) | 77.33 |
| TruthfulQA (0-shot) | 63.91 |
| Winogrande (5-shot) | 84.37 |
| GSM8k (5-shot) | 72.25 |