You can deploy this model and start earning money today!

RichardErkhov/
netcat420_-_MFANNv0.19.12-gguf

Name: netcat420_-_MFANNv0.19.12-gguf
Availability: InStock

2306.01708

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MFANNv0.19.12 - GGUF

Model creator: https://huggingface.co/netcat420/
Original model: https://huggingface.co/netcat420/MFANNv0.19.12/

Name	Quant method	Size
MFANNv0.19.12.Q2_K.gguf	Q2_K	2.17GB
MFANNv0.19.12.IQ3_XS.gguf	IQ3_XS	3.28GB
MFANNv0.19.12.IQ3_S.gguf	IQ3_S	3.43GB
MFANNv0.19.12.Q3_K_S.gguf	Q3_K_S	3.41GB
MFANNv0.19.12.IQ3_M.gguf	IQ3_M	0.41GB
MFANNv0.19.12.Q3_K.gguf	Q3_K	0.01GB
MFANNv0.19.12.Q3_K_M.gguf	Q3_K_M	0.01GB
MFANNv0.19.12.Q3_K_L.gguf	Q3_K_L	0.0GB
MFANNv0.19.12.IQ4_XS.gguf	IQ4_XS	0.0GB
MFANNv0.19.12.Q4_0.gguf	Q4_0	0.0GB
MFANNv0.19.12.IQ4_NL.gguf	IQ4_NL	0.0GB
MFANNv0.19.12.Q4_K_S.gguf	Q4_K_S	0.0GB
MFANNv0.19.12.Q4_K.gguf	Q4_K	0.0GB
MFANNv0.19.12.Q4_K_M.gguf	Q4_K_M	0.0GB
MFANNv0.19.12.Q4_1.gguf	Q4_1	0.0GB
MFANNv0.19.12.Q5_0.gguf	Q5_0	0.0GB
MFANNv0.19.12.Q5_K_S.gguf	Q5_K_S	0.0GB
MFANNv0.19.12.Q5_K.gguf	Q5_K	0.0GB
MFANNv0.19.12.Q5_K_M.gguf	Q5_K_M	0.0GB
MFANNv0.19.12.Q5_1.gguf	Q5_1	0.0GB
MFANNv0.19.12.Q6_K.gguf	Q6_K	0.0GB
MFANNv0.19.12.Q8_0.gguf	Q8_0	0.0GB

Original model description:

base_model:

netcat420/MFANNv0.19
mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
netcat420/MFANNv0.19.11 library_name: transformers tags:
mergekit
merge

MFANNv0.19.12

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

Merge Details

Merge Method

This model was merged using the 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:

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: netcat420/MFANNv0.19.11
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: netcat420/MFANNv0.19
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
merge_method: ties
base_model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
parameters:
  normalize: true
  int8_mask: true
dtype: float16

RichardErkhov/netcat420_-_MFANNv0.19.12-gguf