Files
qwen2.5-1.5b-medical-sft-da…/mergekit_config.yml

12 lines
241 B
YAML
Raw Normal View History

models:
- model: Qwen/Qwen2.5-1.5B-Instruct
- model: outputs/part1/model_sft_full
parameters:
weight: 1.0
density: 0.7
merge_method: dare_linear
base_model: Qwen/Qwen2.5-1.5B-Instruct
parameters:
normalize: false
dtype: bfloat16