iRASC
/

BioLlama-Ko-8B

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

BioLlama-Ko-8B / mergekit_config.yml

taewan2002's picture

Upload folder using huggingface_hub

d78773b verified 5 months ago

268 Bytes

	models:
	- model: ProbeMedicalYonseiMAILab/medllama3-v20
	- model: beomi/Llama-3-Open-Ko-8B
	parameters:
	density: 0.8
	weight: 0.45
	merge_method: dare_ties
	base_model: ProbeMedicalYonseiMAILab/medllama3-v20
	parameters:
	int8_mask: true
	dtype: bfloat16