base_model: d:/DeepSeek-R1-Distill-Qwen-1.5B-uncensored | |
gate_mode: random | |
architecture: qwen | |
dtype: bfloat16 | |
experts_per_token: 2 | |
experts: | |
- source_model: D:/DeepSeek-R1-Distill-Qwen-1.5B | |
- source_model: D:/DeepSeek-R1-Distill-Qwen-1.5B-uncensored | |
shared_experts: | |
- source_model: D:/DeepSeek-R1-Distill-Qwen-1.5B-uncensored | |