merge_method: task_arithmetic | |
base_model: meta-llama/Llama-3.1-70B | |
models: | |
- model: tokyotech-llm/Llama-3.1-Swallow-70B-v0.1 | |
parameters: | |
weight: 1.0 | |
- model: meta-llama/Llama-3.3-70B-Instruct | |
parameters: | |
weight: 0.8 | |
dtype: bfloat16 | |
name: Llama-3.3-FakeSwallow-70B-Instruct-v0.1 |