base_model: meta-llama/Meta-Llama-3-8B-Instruct | |
gate_mode: random | |
dtype: bfloat16 | |
experts_per_token: 2 | |
experts: | |
- source_model: meta-llama/Meta-Llama-3-8B-Instruct | |
positive_prompts: [] | |
- source_model: meta-llama/Meta-Llama-3-8B-Instruct | |
positive_prompts: [] | |
- source_model: meta-llama/Meta-Llama-3-8B-Instruct | |
positive_prompts: [] | |
- source_model: meta-llama/Meta-Llama-3-8B-Instruct | |
positive_prompts: [] | |