Qwen2.5-Coder-7B_karasu_mergeTIES / mergekit_config.yml
noirchan's picture
Upload folder using huggingface_hub
a907760 verified
raw
history blame
399 Bytes
models:
- model: Qwen/Qwen2.5-Coder-7B-Instruct
#no parameters necessary for base model
- model: lightblue/Karasu-DPO-7B
parameters:
density: 0.5
weight: 0.5
- model: Qwen/Qwen2.5-Coder-7B-Instruct
parameters:
density: 0.5
weight: 0.5
merge_method: ties
base_model: Qwen/Qwen2.5-7B-Instruct
parameters:
normalize: false
int8_mask: true
dtype: float16