Quantization made by Richard Erkhov.

Phenom-12B-0.1 - GGUF

Model creator: https://huggingface.co/Bacon666/
Original model: https://huggingface.co/Bacon666/Phenom-12B-0.1/

Name	Quant method	Size
Phenom-12B-0.1.Q2_K.gguf	Q2_K	4.46GB
Phenom-12B-0.1.Q3_K_S.gguf	Q3_K_S	5.15GB
Phenom-12B-0.1.Q3_K.gguf	Q3_K	5.67GB
Phenom-12B-0.1.Q3_K_M.gguf	Q3_K_M	5.67GB
Phenom-12B-0.1.Q3_K_L.gguf	Q3_K_L	6.11GB
Phenom-12B-0.1.IQ4_XS.gguf	IQ4_XS	6.33GB
Phenom-12B-0.1.Q4_0.gguf	Q4_0	6.59GB
Phenom-12B-0.1.IQ4_NL.gguf	IQ4_NL	6.65GB
Phenom-12B-0.1.Q4_K_S.gguf	Q4_K_S	6.63GB
Phenom-12B-0.1.Q4_K.gguf	Q4_K	6.96GB
Phenom-12B-0.1.Q4_K_M.gguf	Q4_K_M	6.96GB
Phenom-12B-0.1.Q4_1.gguf	Q4_1	7.26GB
Phenom-12B-0.1.Q5_0.gguf	Q5_0	7.93GB
Phenom-12B-0.1.Q5_K_S.gguf	Q5_K_S	7.93GB
Phenom-12B-0.1.Q5_K.gguf	Q5_K	8.13GB
Phenom-12B-0.1.Q5_K_M.gguf	Q5_K_M	8.13GB
Phenom-12B-0.1.Q5_1.gguf	Q5_1	8.61GB
Phenom-12B-0.1.Q6_K.gguf	Q6_K	9.37GB
Phenom-12B-0.1.Q8_0.gguf	Q8_0	12.13GB

Original model description:

base_model:

anthracite-org/magnum-v2.5-12b-kto
TheDrummer/Rocinante-12B-v1.1
MarinaraSpaghetti/NemoMix-Unleashed-12B
elinas/Chronos-Gold-12B-1.0 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 della_linear merge method using TheDrummer/Rocinante-12B-v1.1 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: MarinaraSpaghetti/NemoMix-Unleashed-12B
    parameters:
      weight: 0.25
      density: 0.84
  - model: elinas/Chronos-Gold-12B-1.0
    parameters:
      weight: 0.4
      density: 0.88
  - model: anthracite-org/magnum-v2.5-12b-kto
    parameters:
      weight: 0.6
      density: 0.9
merge_method: della_linear
base_model: TheDrummer/Rocinante-12B-v1.1
parameters:
  int8_mask: true
  epsilon: 0.07
  lambda: 1
dtype: bfloat16