noirchan
/

Llama-3-8B-suzume_liner0.8

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Llama-3-8B-suzume_liner0.8 / mergekit_config.yml

noirchan's picture

Upload folder using huggingface_hub

e9d7738 verified 24 days ago

history blame contribute delete

208 Bytes


	models:
	- model: meta-llama/Meta-Llama-3-8B-Instruct
	parameters:
	weight: 0.8
	- model: lightblue/suzume-llama-3-8B-japanese
	parameters:
	weight: 0.2
	merge_method: linear
	dtype: float16