Name	Quant method	Size
MFANNv0.19.10.Q2_K.gguf	Q2_K	2.96GB
MFANNv0.19.10.IQ3_XS.gguf	IQ3_XS	3.28GB
MFANNv0.19.10.IQ3_S.gguf	IQ3_S	3.43GB
MFANNv0.19.10.Q3_K_S.gguf	Q3_K_S	3.41GB
MFANNv0.19.10.IQ3_M.gguf	IQ3_M	3.52GB
MFANNv0.19.10.Q3_K.gguf	Q3_K	3.74GB
MFANNv0.19.10.Q3_K_M.gguf	Q3_K_M	1.17GB
MFANNv0.19.10.Q3_K_L.gguf	Q3_K_L	4.03GB
MFANNv0.19.10.IQ4_XS.gguf	IQ4_XS	4.18GB
MFANNv0.19.10.Q4_0.gguf	Q4_0	4.34GB
MFANNv0.19.10.IQ4_NL.gguf	IQ4_NL	4.38GB
MFANNv0.19.10.Q4_K_S.gguf	Q4_K_S	4.37GB
MFANNv0.19.10.Q4_K.gguf	Q4_K	0.41GB
MFANNv0.19.10.Q4_K_M.gguf	Q4_K_M	0.64GB
MFANNv0.19.10.Q4_1.gguf	Q4_1	4.78GB
MFANNv0.19.10.Q5_0.gguf	Q5_0	5.21GB
MFANNv0.19.10.Q5_K_S.gguf	Q5_K_S	5.21GB
MFANNv0.19.10.Q5_K.gguf	Q5_K	5.34GB
MFANNv0.19.10.Q5_K_M.gguf	Q5_K_M	5.34GB
MFANNv0.19.10.Q5_1.gguf	Q5_1	5.65GB
MFANNv0.19.10.Q6_K.gguf	Q6_K	6.14GB
MFANNv0.19.10.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
netcat420/MFANNv0.19 library_name: transformers tags:
mergekit
merge

MFANNv0.19.10

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 mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated as a base.

Models Merged

The following models were included in the merge:

netcat420/MFANNv0.19

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
    # No parameters necessary for base model
  - model: netcat420/MFANNv0.19
    parameters:
      density: 0.53
      weight: 0.5
merge_method: dare_ties
base_model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
parameters:
  int8_mask: true
dtype: bfloat16

RichardErkhov/netcat420_-_MFANNv0.19.10-gguf