Quantization made by Richard Erkhov.

MFANNv0.17.12 - GGUF

Model creator: https://huggingface.co/netcat420/
Original model: https://huggingface.co/netcat420/MFANNv0.17.12/

Name	Quant method	Size
MFANNv0.17.12.Q2_K.gguf	Q2_K	0.75GB
MFANNv0.17.12.Q3_K_S.gguf	Q3_K_S	3.41GB
MFANNv0.17.12.Q3_K.gguf	Q3_K	3.74GB
MFANNv0.17.12.Q3_K_M.gguf	Q3_K_M	3.74GB
MFANNv0.17.12.Q3_K_L.gguf	Q3_K_L	4.03GB
MFANNv0.17.12.IQ4_XS.gguf	IQ4_XS	4.18GB
MFANNv0.17.12.Q4_0.gguf	Q4_0	4.34GB
MFANNv0.17.12.IQ4_NL.gguf	IQ4_NL	4.38GB
MFANNv0.17.12.Q4_K_S.gguf	Q4_K_S	4.37GB
MFANNv0.17.12.Q4_K.gguf	Q4_K	4.58GB
MFANNv0.17.12.Q4_K_M.gguf	Q4_K_M	4.58GB
MFANNv0.17.12.Q4_1.gguf	Q4_1	4.78GB
MFANNv0.17.12.Q5_0.gguf	Q5_0	5.21GB
MFANNv0.17.12.Q5_K_S.gguf	Q5_K_S	5.21GB
MFANNv0.17.12.Q5_K.gguf	Q5_K	5.34GB
MFANNv0.17.12.Q5_K_M.gguf	Q5_K_M	5.34GB
MFANNv0.17.12.Q5_1.gguf	Q5_1	5.65GB
MFANNv0.17.12.Q6_K.gguf	Q6_K	6.14GB
MFANNv0.17.12.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

netcat420/MFANNv0.17
netcat420/MFANNv0.17.11
MaziyarPanahi/Llama-3-8B-Instruct-v0.4 library_name: transformers tags:
mergekit
merge

MFANNv0.17.12

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 MaziyarPanahi/Llama-3-8B-Instruct-v0.4 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: netcat420/MFANNv0.17.11
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: netcat420/MFANNv0.17
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
merge_method: ties
base_model: MaziyarPanahi/Llama-3-8B-Instruct-v0.4
parameters:
  normalize: true
  int8_mask: true
dtype: float16