QuantFactory/SAINEMO-reMIX-GGUF

This is quantized version of Moraliane/SAINEMO-reMIX created using llama.cpp

Original Model Card

SAINEMO-reMIX

GGUF: thx team mradermacher

https://huggingface.co/mradermacher/SAINEMO-reMIX-GGUF

GGUF imatrix

https://huggingface.co/mradermacher/SAINEMO-reMIX-i1-GGUF

learderboard

Presets

The given presets are quite suitable for this model. https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main/Customized/Mistral%20Improved

Sampler

Temp - 0,7 - 1,2 ~
TopA - 0,1
DRY - 0,8 1,75 2 0
I recommend trying the stock presets from SillyTavern, such as simple-1.

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 E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b as a base.

Models Merged

The following models were included in the merge:

• E:\Programs\TextGen\text-generation-webui\models\elinas_Chronos-Gold-12B-1.0
• E:\Programs\TextGen\text-generation-webui\models\Vikhrmodels_Vikhr-Nemo-12B-Instruct-R-21-09-24
• E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
    parameters:
      weight: 0.55  # Основной акцент на русском языке
      density: 0.4
  - model: E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
    parameters:
      weight: 0.2  # РП модель, чуть меньший вес из-за ориентации на английский
      density: 0.4
  - model: E:\Programs\TextGen\text-generation-webui\models\elinas_Chronos-Gold-12B-1.0
    parameters:
      weight: 0.15  # Вторая РП модель
      density: 0.4
  - model: E:\Programs\TextGen\text-generation-webui\models\Vikhrmodels_Vikhr-Nemo-12B-Instruct-R-21-09-24
    parameters:
      weight: 0.25  # Русскоязычная поддержка и баланс
      density: 0.4

merge_method: della_linear
base_model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
parameters:
  epsilon: 0.05
  lambda: 1
dtype: float16
tokenizer_source: base