Zoyd
/

giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-8_0bpw_exl2

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

giannisan_Mistral-10.7B-Instruct-v0.3-depth-upscaling-8_0bpw_exl2 / mergekit_config.yml

Zoyd's picture

Upload folder using huggingface_hub

29f4cef verified over 1 year ago

history blame contribute delete

233 Bytes

	slices:
	- sources:
	- model: mistralai/Mistral-7B-Instruct-v0.3
	layer_range: [0, 24]
	- sources:
	- model: mistralai/Mistral-7B-Instruct-v0.3
	layer_range: [8, 32]
	merge_method: passthrough
	dtype: bfloat16