metadata
base_model:
- arcee-ai/Llama-3.1-SuperNova-Lite
library_name: transformers
tags:
- mergekit
- merge
chubby10b
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
dtype: bfloat16
merge_method: passthrough
parameters:
int8_mask: 1.0
slices:
- sources:
- layer_range: [0, 24]
model: arcee-ai/Llama-3.1-SuperNova-Lite
- sources:
- layer_range: [18, 28]
model: arcee-ai/Llama-3.1-SuperNova-Lite
parameters:
scale:
- filter: o_proj
value: 0.2
- filter: down_proj
value: 0.2
- sources:
- layer_range: [24, 32]
model: arcee-ai/Llama-3.1-SuperNova-Lite