RichardErkhov/ClaudioItaly_-_Pullulation-2-9B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Pullulation-2-9B - GGUF

• Model creator: https://huggingface.co/ClaudioItaly/
• Original model: https://huggingface.co/ClaudioItaly/Pullulation-2-9B/

Name	Quant method	Size
Pullulation-2-9B.Q2_K.gguf	Q2_K	3.54GB
Pullulation-2-9B.IQ3_XS.gguf	IQ3_XS	3.86GB
Pullulation-2-9B.IQ3_S.gguf	IQ3_S	4.04GB
Pullulation-2-9B.Q3_K_S.gguf	Q3_K_S	4.04GB
Pullulation-2-9B.IQ3_M.gguf	IQ3_M	4.19GB
Pullulation-2-9B.Q3_K.gguf	Q3_K	4.43GB
Pullulation-2-9B.Q3_K_M.gguf	Q3_K_M	4.43GB
Pullulation-2-9B.Q3_K_L.gguf	Q3_K_L	4.78GB
Pullulation-2-9B.IQ4_XS.gguf	IQ4_XS	4.86GB
Pullulation-2-9B.Q4_0.gguf	Q4_0	5.07GB
Pullulation-2-9B.IQ4_NL.gguf	IQ4_NL	5.1GB
Pullulation-2-9B.Q4_K_S.gguf	Q4_K_S	5.1GB
Pullulation-2-9B.Q4_K.gguf	Q4_K	5.37GB
Pullulation-2-9B.Q4_K_M.gguf	Q4_K_M	5.37GB
Pullulation-2-9B.Q4_1.gguf	Q4_1	5.55GB
Pullulation-2-9B.Q5_0.gguf	Q5_0	6.04GB
Pullulation-2-9B.Q5_K_S.gguf	Q5_K_S	6.04GB
Pullulation-2-9B.Q5_K.gguf	Q5_K	6.19GB
Pullulation-2-9B.Q5_K_M.gguf	Q5_K_M	6.19GB
Pullulation-2-9B.Q5_1.gguf	Q5_1	6.52GB
Pullulation-2-9B.Q6_K.gguf	Q6_K	7.07GB
Pullulation-2-9B.Q8_0.gguf	Q8_0	9.15GB

Original model description:

base_model:

• jsgreenawalt/gemma-2-9B-it-advanced-v2.1
• nbeerbower/gemma2-gutenberg-9B
• ifable/gemma-2-Ifable-9B
• UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
• lemon07r/Gemma-2-Ataraxy-9B
• BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference 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 Model Stock merge method using nbeerbower/gemma2-gutenberg-9B as a base.

Models Merged

The following models were included in the merge:

• jsgreenawalt/gemma-2-9B-it-advanced-v2.1
• ifable/gemma-2-Ifable-9B
• UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
• lemon07r/Gemma-2-Ataraxy-9B
• BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: nbeerbower/gemma2-gutenberg-9B
    parameters:
      weight: 0.25
  - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    parameters:
      weight: 0.25
  - model: ifable/gemma-2-Ifable-9B
    parameters:
      weight: 0.25
  - model: jsgreenawalt/gemma-2-9B-it-advanced-v2.1
    parameters:
      weight: 0.25
  - model: lemon07r/Gemma-2-Ataraxy-9B
    parameters:
      weight: 0.25
  - model: BAAI/Gemma2-9B-IT-Simpo-Infinity-Preference
    parameters:
      weight: 0.25

base_model: nbeerbower/gemma2-gutenberg-9B  # Modello di riferimento per la fusione

parameters:
  t: [0, 0.33, 0.67, 1]  # Parametri di interpolazione
dtype: bfloat16
merge_method: model_stock  # Metodo di fusione