Working Merge in my Profile
Collection
20 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the della merge method using kromeurus/L3.1-Aglow-Vulca-v0.1-8B as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: Casual-Autopsy/L3-Super-Nova-RP-8B
parameters:
density: 0.5
weight: 0.27
- model: TheDrummer/Llama-3SOME-8B-v2
parameters:
density: 0.6
weight: 0.23
- model: djuna/L3.1-Noraian
parameters:
density: 0.4
weight: 0.28
merge_method: della
base_model: kromeurus/L3.1-Aglow-Vulca-v0.1-8B
parameters:
epsilon: 0.1
lambda: 1.0
normalize: false
int8_mask: true
dtype: float32
out_dtype: bfloat16