metadata
base_model:
- Alelcv27/llama3-8b-code-dpo
- Alelcv27/llama3-8b-math-dpo
library_name: transformers
tags:
- mergekit
- merge
llama3-8b-slerp-v2
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: Alelcv27/llama3-8b-math-dpo
dtype: float16
merge_method: slerp
parameters:
t: 0.3
slices:
- sources:
- layer_range: [0, 32]
model: Alelcv27/llama3-8b-math-dpo
- layer_range: [0, 32]
model: Alelcv27/llama3-8b-code-dpo