| models: | |
| - model: tokyotech-llm/Swallow-70b-instruct-hf | |
| # no parameters necessary for base model | |
| - model: allenai/tulu-2-dpo-70b # follow user intent | |
| parameters: | |
| density: 1 | |
| weight: | |
| - filter: mlp | |
| value: 0.1 | |
| - filter: self_attn | |
| value: 0.45 | |
| - value: 0 # fallback for rest of tensors. | |
| merge_method: dare_ties | |
| base_model: tokyotech-llm/Swallow-70b-instruct-hf | |
| dtype: bfloat16 | |
| tokenizer_source: union | |