Resolving Interference When Merging Models
Paper • 2306.01708 • Published • 18
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
A TIES merge with PsyMedRP, MLewd-ReMM-L2-Chat-20B-Inverted and PsyMedLewd-20B-TIES :
Undi95/MLewd-ReMM-L2-Chat-20B-Inverted
Feels like the best all rounder from the PsyMedLewd series. Still in testing but so far I like it's creativity and occasional wacky humour.
RECOMMENDED SETTINGS FOR ALL PsyMedLewd VERSIONS
(based on KoboldCPP):
Temperature - 1.3
Max Ctx. Tokens - 4096
Top p Sampling - 0.99
Repetition Penalty - 1.09
Amount to Gen. - 512
Prompt template: Alpaca or ChatML
#################################################################################################################################################
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the TIES merge method using Undi95/PsyMedRP-v1-20B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
models:
- model: Undi95/PsyMedRP-v1-20B
parameters:
density: 0.7
weight: 0.6
- model: Elfrino/PsyMedLewd-20B-TIES
parameters:
density: 0.5
weight: 0.4
- model: Undi95/MLewd-ReMM-L2-Chat-20B-Inverted
parameters:
density: 0.4
weight: 0.3
merge_method: ties
base_model: Undi95/PsyMedRP-v1-20B
parameters:
normalize: false
int8_mask: true
dtype: float16
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support