metadata
base_model:
- Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
- IlyaGusev/vikhr_nemo_orpo_dostoevsky_12b
datasets:
- 40umov/dostoevsky
language:
- ru
library_name: mergekit
tags:
- mergekit
- merge
A merge of vikhr_nemo_orpo_dostoevsky_12b and Vikhr-Nemo-12B-Instruct-R-21-09-24
Merge Details
Merge Method
This is a merge of pre-trained language models created using mergekit. This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
- vikhr_nemo_orpo_dostoevsky_12b
- Vikhr-Nemo-12B-Instruct-R-21-09-24
Configuration
The following YAML configuration was used to produce this model:
base_model: vikhr_nemo_orpo_dostoevsky_12b
dtype: bfloat16
merge_method: slerp
parameters:
t:
- filter: self_attn
value: [0.0, 0.5, 0.3, 0.7, 1.0]
- filter: mlp
value: [1.0, 0.5, 0.7, 0.3, 0.0]
- value: 0.5
slices:
- sources:
- layer_range: [0, 40]
model: Vikhr-Nemo-12B-Instruct-R-21-09-24
- layer_range: [0, 40]
model: vikhr_nemo_orpo_dostoevsky_12b