QAIMath-Qwen2.5-7B-TIES / mergekit_config.yml
adriszmar's picture
Upload folder using huggingface_hub
c89bc16 verified
raw
history blame
280 Bytes
models:
- model: Qwen/Qwen2.5-Math-7B
parameters:
density: 0.5
weight: 0.4
- model: Qwen/Qwen2.5-Math-7B-Instruct
parameters:
density: 0.5
weight: 0.3
merge_method: ties
base_model: Qwen/Qwen2.5-7B
parameters:
normalize: true
dtype: float16