Quantization made by Richard Erkhov.

MFANN3bv0.19.10 - GGUF

Model creator: https://huggingface.co/netcat420/
Original model: https://huggingface.co/netcat420/MFANN3bv0.19.10/

Name	Quant method	Size
MFANN3bv0.19.10.Q2_K.gguf	Q2_K	1.03GB
MFANN3bv0.19.10.IQ3_XS.gguf	IQ3_XS	1.12GB
MFANN3bv0.19.10.IQ3_S.gguf	IQ3_S	1.16GB
MFANN3bv0.19.10.Q3_K_S.gguf	Q3_K_S	1.16GB
MFANN3bv0.19.10.IQ3_M.gguf	IQ3_M	1.23GB
MFANN3bv0.19.10.Q3_K.gguf	Q3_K	1.33GB
MFANN3bv0.19.10.Q3_K_M.gguf	Q3_K_M	1.33GB
MFANN3bv0.19.10.Q3_K_L.gguf	Q3_K_L	1.47GB
MFANN3bv0.19.10.IQ4_XS.gguf	IQ4_XS	1.43GB
MFANN3bv0.19.10.Q4_0.gguf	Q4_0	1.49GB
MFANN3bv0.19.10.IQ4_NL.gguf	IQ4_NL	1.5GB
MFANN3bv0.19.10.Q4_K_S.gguf	Q4_K_S	1.51GB
MFANN3bv0.19.10.Q4_K.gguf	Q4_K	1.62GB
MFANN3bv0.19.10.Q4_K_M.gguf	Q4_K_M	1.62GB
MFANN3bv0.19.10.Q4_1.gguf	Q4_1	1.65GB
MFANN3bv0.19.10.Q5_0.gguf	Q5_0	1.8GB
MFANN3bv0.19.10.Q5_K_S.gguf	Q5_K_S	1.8GB
MFANN3bv0.19.10.Q5_K.gguf	Q5_K	1.87GB
MFANN3bv0.19.10.Q5_K_M.gguf	Q5_K_M	1.87GB
MFANN3bv0.19.10.Q5_1.gguf	Q5_1	1.95GB
MFANN3bv0.19.10.Q6_K.gguf	Q6_K	2.13GB
MFANN3bv0.19.10.Q8_0.gguf	Q8_0	2.75GB

Original model description:

base_model:

netcat420/MFANN3bv0.18.11
netcat420/MFANN3bv0.19
liminerity/Phigments12
netcat420/MFANN3bv0.6 library_name: transformers tags:
mergekit
merge

MFANN3bv0.19.10

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using liminerity/Phigments12 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: liminerity/Phigments12
    # No parameters necessary for base model
  - model: netcat420/MFANN3bv0.19
    parameters:
      density: 0.53
      weight: 0.5
  - model: netcat420/MFANN3bv0.6
    parameters:
      density: 0.53
      weight: 0.3
  - model: netcat420/MFANN3bv0.18.11
    parameters:
      density: 0.53
      weight: 0.2
merge_method: dare_ties
base_model: liminerity/Phigments12
parameters:
  int8_mask: true
dtype: bfloat16