merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the della_linear merge method using Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
    parameters:
      weight: 0.55
      density: 0.4
  - model: IlyaGusev/saiga_nemo_12b
    parameters:
      weight: 0.35
      density: 0.4
  - model: IlyaGusev/vikhr_nemo_orpo_dostoevsky_12b
    parameters:
      weight: 0.25
      density: 0.4
merge_method: della_linear
base_model: Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
parameters:
  epsilon: 0.05
  lambda: 1
dtype: float16
tokenizer_source: base
Downloads last month
47
Safetensors
Model size
12.2B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for rityak/Vikhr-Nemo-dostoevsky-saiga-12b