| base_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b | |
| gate_mode: hidden | |
| architecture: qwen | |
| dtype: bfloat16 | |
| experts_per_token: 2 | |
| experts: | |
| - source_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b | |
| positive_prompts: | |
| - "chat" | |
| - "assistant" | |
| - "explain" | |
| - "describe" | |
| - "define" | |
| - "what is" | |
| - "tell me" | |
| - "help me" | |
| - "show me" | |
| - "can you" | |
| - source_model: macadeliccc/Samantha-Qwen2-1.5B | |
| positive_prompts: | |
| - "characters" | |
| - "scene" | |
| - "roleplay" | |
| - "writing" | |
| - "creative" | |
| - "you are" | |
| - "act as" | |
| shared_experts: | |
| - source_model: cognitivecomputations/dolphin-2.9.3-qwen2-1.5b | |
| positive_prompts: # required by Qwen MoE for "hidden" gate mode, otherwise not allowed | |
| - "chat" | |
| - "assistant" | |
| # (optional, but recommended:) | |
| residual_scale: 0.1 | |