wraithbaron
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the DELLA merge method using kromcomp/L3.1-Tarnishedv8-12B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: kromcomp/L3.1-Tarnishedv8-12B
chat_template: llama3
dtype: float32
merge_method: della
modules:
default:
slices:
- sources:
- layer_range: [0, 50]
model: kromcomp/L3.1-Mantlev1-12B
parameters:
density: 0.4
epsilon: 0.1
lambda: 1.05
weight: [0.1, 0.2, 0.4]
- layer_range: [0, 50]
model: kromcomp/L3.1-Legionv2-12B
parameters:
density: 0.55
epsilon: 0.15
lambda: 1.05
weight: [0.4, 0.5, 0.4]
- layer_range: [0, 50]
model: kromcomp/L3.1-Groundsv1-12B
parameters:
density: 0.45
epsilon: 0.15
lambda: 1.0
weight: [0.5, 0.3, 0.2]
- layer_range: [0, 50]
model: kromcomp/L3.1-Tarnishedv8-12B
parameters:
int8_mask: 1.0
normalize: 0.0
tokenizer:
pad_to_multiple_of: 32
- Downloads last month
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support