README.md

metadata

base_model:
  - nbeerbower/mistral-nemo-gutenberg-12B-v2
  - nbeerbower/Stella-mistral-nemo-12B-v2
library_name: transformers
tags:
  - mergekit
  - merge

merge

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:

• nbeerbower/mistral-nemo-gutenberg-12B-v2
• nbeerbower/Stella-mistral-nemo-12B-v2

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/Stella-mistral-nemo-12B-v2
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v2

merge_method: slerp
tokenizer_merge_method: slerp
tokenizer_parameters:
  t: 0.45  # Bilanciamento più equilibrato tra i due tokenizer

base_model: nbeerbower/mistral-nemo-gutenberg-12B-v2
dtype: float32  # Impostato su float32

parameters:
  t: [0, 0.3, 0.5, 0.4, 0.3, 0]  # Curva più equilibrata
  temp: 1.5  # Temperatura leggermente aumentata per maggiore creatività

density:
  - threshold: 0.2
    t: 0.6
  - threshold: 0.7
    t: 0.4
  - threshold: 0.9
    t: 0.35