gate_mode: hidden | |
architecture: qwen | |
dtype: bfloat16 | |
experts_per_token: 2 | |
base_model: M4-ai/Hercules-5.0-Qwen2-1.5B | |
experts: | |
- source_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b | |
positive_prompts: | |
- "explain" | |
- "describe" | |
- "define" | |
- "help" | |
- "assist" | |
- source_model: Replete-AI/Qwen2-1.5b-Instruct-Replete-Adapted | |
positive_prompts: | |
- "code" | |
- "algorithm" | |
- "programming" | |
- "development" | |
- "software" | |
- "framework" | |
- source_model: M4-ai/Hercules-5.0-Qwen2-1.5B | |
positive_prompts: | |
- "rewrite" | |
- "paraphrase" | |
- "translate" | |
- "reword" | |
- source_model: d-llm/Qwen2-1.5B-Instruct-orpo | |
positive_prompts: | |
- "summarize" | |
- "shorten" | |
- "condense" | |
- "tldr" | |
shared_experts: | |
- source_model: M4-ai/Hercules-5.0-Qwen2-1.5B | |
positive_prompts: # required by Qwen MoE for "hidden" gate mode, otherwise not allowed | |
- "assistant" | |
- "chat" | |
# (optional, but recommended:) | |
residual_scale: 0.1 | |