| base_model: Meta-Llama-3-8B-Instruct | |
| experts: | |
| - source_model: Meta-Llama-3-8B-Instruct | |
| positive_prompts: | |
| - "explain" | |
| - "chat" | |
| - "assistant" | |
| - "think" | |
| - "roleplay" | |
| - "versatile" | |
| - "helpful" | |
| - "factual" | |
| - "integrated" | |
| - "adaptive" | |
| - "comprehensive" | |
| - "balanced" | |
| negative_prompts: | |
| - "specialized" | |
| - "narrow" | |
| - "focused" | |
| - "limited" | |
| - "specific" | |
| - source_model: ChatQA-1.5-8B | |
| positive_prompts: | |
| - "python" | |
| - "math" | |
| - "solve" | |
| - "code" | |
| - "programming" | |
| negative_prompts: | |
| - "sorry" | |
| - "cannot" | |
| - "factual" | |
| - "concise" | |
| - "straightforward" | |
| - "objective" | |
| - "dry" | |
| - source_model: SFR-Iterative-DPO-LLaMA-3-8B-R | |
| positive_prompts: | |
| - "chat" | |
| - "assistant" | |
| - "AI" | |
| - "instructive" | |
| - "clear" | |
| - "directive" | |
| - "helpful" | |
| - "informative" | |
| - source_model: Llama3-8B-OpenHermes-DPO | |
| positive_prompts: | |
| - "analytical" | |
| - "accurate" | |
| - "logical" | |
| - "knowledgeable" | |
| - "precise" | |
| - "calculate" | |
| - "compute" | |
| - "solve" | |
| - "work" | |
| - "python" | |
| - "code" | |
| - "javascript" | |
| - "programming" | |
| - "algorithm" | |
| - "tell me" | |
| - "assistant" | |
| negative_prompts: | |
| - "creative" | |
| - "abstract" | |
| - "imaginative" | |
| - "artistic" | |
| - "emotional" | |
| - "mistake" | |
| - "inaccurate" | |
| gate_mode: hidden | |
| dtype: float16 | |