| base_model: tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1 | |
| models: | |
| - model: tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.1 | |
| # No parameters necessary for base model | |
| - model: NousResearch/Hermes-3-Llama-3.1-8B | |
| parameters: | |
| density: 0.525 | |
| weight: 1 | |
| merge_method: dare_ties | |
| tokenizer_source: union | |
| dtype: bfloat16 | |