Puffin-Qwen2.5-CodeMath / mergekit_config.yml
chargoddard's picture
Upload folder using huggingface_hub
6a2ef4f verified
raw
history blame contribute delete
262 Bytes
models:
- model: Qwen/Qwen2.5-Math-1.5B
- model: Qwen/Qwen2.5-Coder-1.5B
merge_method: slerp
base_model: Qwen/Qwen2.5-Math-1.5B
dtype: bfloat16
parameters:
t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers