| merge_method: task_arithmetic | |
| base_model: meta-llama/Llama-3.1-70B-Instruct | |
| models: | |
| - model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | |
| parameters: | |
| weight: 1.0 | |
| - model: meta-llama/Llama-3.3-70B-Instruct | |
| parameters: | |
| weight: 1.0 | |
| dtype: bfloat16 | |
| out_dtype: bfloat16 | |
| parameters: | |
| int8_mask: true | |
| normalize: false | |
| rescale: false | |
| filter_wise: false | |
| chat_template: auto | |
| tokenizer: | |
| source: union |