kechengcode
/

Llama-3.1-5B-Instruct-18Layers

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Llama-3.1-5B-Instruct-18Layers / mergekit_config.yml

kechengcode's picture

Upload folder using huggingface_hub

e8947a4 verified 3 months ago

218 Bytes

	dtype: float16
	merge_method: passthrough
	slices:
	- sources:
	- layer_range: [0, 6]
	model: meta-llama/Meta-Llama-3.1-8B-Instruct
	- sources:
	- layer_range: [20, 32]
	model: meta-llama/Meta-Llama-3.1-8B-Instruct