Masterjp123
/

SnowyRP-FinalV1-L2-13B-GPTQ

Text Generation

Not-For-All-Audiences

text-generation-inference

Model card Files Files and versions Community

SnowyRP-FinalV1-L2-13B-GPTQ / mega-snowRP.yml

Masterjp123's picture

Upload 8 files

d291a44 verified 5 months ago

raw history blame contribute delete

No virus

1.28 kB

	base_model: TheBloke/Llama-2-13B-fp16
	models:
	- model: TheBloke/Llama-2-13B-fp16
	- model: Undi95/Unholy-v2-13B
	parameters:
	weight: 1.0
	- model: Henk717/echidna-tiefigther-25
	parameters:
	weight: 0.45
	- model: KoboldAI/LLaMA2-13B-Erebus-v3
	parameters:
	weight: 0.33
	dtype: bfloat16
	merge_method: task_arithmetic
	name: SnowyRP-13B-L2-P1
	---
	base_model: TheBloke/Llama-2-13B-fp16
	models:
	- model: TheBloke/Llama-2-13B-fp16
	- model: KoboldAI/LLaMA2-13B-Psyfighter2
	parameters:
	weight: 1.0
	- model: Riiid/sheep-duck-llama-2-13b
	parameters:
	weight: 0.45
	- model: IkariDev/Athena-v4
	parameters:
	weight: 0.33
	dtype: bfloat16
	merge_method: task_arithmetic
	name: SnowyRP-13B-L2-P2
	---
	models:
	- model: ddh0/EstopianOrcaMaid-13b
	parameters:
	density: [1, 0.7, 0.1] # density gradient
	weight: 1.0
	- model: SnowyRP-13B-L2-P2
	parameters:
	density: 0.5
	weight: [0, 0.3, 0.7, 1] # weight gradient
	- model: SnowyRP-13B-L2-P1
	parameters:
	density: 0.33
	weight:
	- filter: mlp
	value: 0.5
	- value: 0
	merge_method: ties
	base_model: TheBloke/Llama-2-13B-fp16
	parameters:
	normalize: true
	int8_mask: true
	dtype: bfloat16
	name: SnowyRP-13B-L2-Final-V1