Llama-3-8B_Suzume_DARE0.5 / mergekit_config.yml
noirchan's picture
Upload folder using huggingface_hub
033cec0 verified
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct
# No parameters necessary for base model
- model: lightblue/suzume-llama-3-8B-japanese
parameters:
density: 0.5
weight: 0.5
merge_method: dare_ties
base_model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
int8_mask: true
dtype: bfloat16