CoolFace
Modelpublic

RichardErkhov/netcat420_-_MFANNv0.20.10-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes712downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

MFANNv0.20.10 - GGUF

  • —Model creator: https://huggingface.co/netcat420/
  • —Original model: https://huggingface.co/netcat420/MFANNv0.20.10/
NameQuant methodSize
MFANNv0.20.10.Q2_K.ggufQ2_K2.96GB
MFANNv0.20.10.IQ3_XS.ggufIQ3_XS3.28GB
MFANNv0.20.10.IQ3_S.ggufIQ3_S3.43GB
MFANNv0.20.10.Q3_K_S.ggufQ3KS3.41GB
MFANNv0.20.10.IQ3_M.ggufIQ3_M3.52GB
MFANNv0.20.10.Q3_K.ggufQ3_K3.74GB
MFANNv0.20.10.Q3_K_M.ggufQ3KM3.74GB
MFANNv0.20.10.Q3_K_L.ggufQ3KL4.03GB
MFANNv0.20.10.IQ4_XS.ggufIQ4_XS4.18GB
MFANNv0.20.10.Q4_0.ggufQ4_04.34GB
MFANNv0.20.10.IQ4_NL.ggufIQ4_NL4.38GB
MFANNv0.20.10.Q4_K_S.ggufQ4KS4.37GB
MFANNv0.20.10.Q4_K.ggufQ4_K4.58GB
MFANNv0.20.10.Q4_K_M.ggufQ4KM4.58GB
MFANNv0.20.10.Q4_1.ggufQ4_14.78GB
MFANNv0.20.10.Q5_0.ggufQ5_05.21GB
MFANNv0.20.10.Q5_K_S.ggufQ5KS5.21GB
MFANNv0.20.10.Q5_K.ggufQ5_K5.34GB
MFANNv0.20.10.Q5_K_M.ggufQ5KM5.34GB
MFANNv0.20.10.Q5_1.ggufQ5_15.65GB
MFANNv0.20.10.Q6_K.ggufQ6_K6.14GB
MFANNv0.20.10.Q8_0.ggufQ8_07.95GB

Original model description: --- base_model:

  • —netcat420/MFANNv0.19
  • —mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
  • —netcat420/MFANNv0.20 library_name: transformers tags:
  • —mergekit
  • —merge

MFANNv0.20.10

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:

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/MFANNv0.20
    parameters:
      density: 0.53
      weight: 0.5
  - 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