jtatman
/

Tiny-Llama-Llama-Dolphin-laser-1b-merge

Text Generation

TinyLlama/TinyLlama-1.1B-Chat-v1.0

cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser

cognitivecomputations/TinyDolphin-2.8.1-1.1b

TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Tiny-Llama-Llama-Dolphin-laser-1b-merge / mergekit_config.yml

jtatman's picture

Upload folder using huggingface_hub

4f1facf verified 8 months ago

410 Bytes


	models:
	- model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
	parameters:
	weight: 1.0
	- model: cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser
	parameters:
	weight: 1.0
	- model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
	parameters:
	weight: 0.4
	- model: TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T
	parameters:
	weight: 0.6
	merge_method: linear
	dtype: float16