CoolFace
Modelpublic

RichardErkhov/Hjgugugjhuhjggg_-_mergekit-ties-fhzafeq-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes1.1kdownloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-ties-fhzafeq - GGUF

  • —Model creator: https://huggingface.co/Hjgugugjhuhjggg/
  • —Original model: https://huggingface.co/Hjgugugjhuhjggg/mergekit-ties-fhzafeq/
NameQuant methodSize
mergekit-ties-fhzafeq.Q2_K.ggufQ2_K1.39GB
mergekit-ties-fhzafeq.IQ3_XS.ggufIQ3_XS1.53GB
mergekit-ties-fhzafeq.IQ3_S.ggufIQ3_S1.59GB
mergekit-ties-fhzafeq.Q3_K_S.ggufQ3KS1.59GB
mergekit-ties-fhzafeq.IQ3_M.ggufIQ3_M1.65GB
mergekit-ties-fhzafeq.Q3_K.ggufQ3_K1.73GB
mergekit-ties-fhzafeq.Q3_K_M.ggufQ3KM1.73GB
mergekit-ties-fhzafeq.Q3_K_L.ggufQ3KL1.85GB
mergekit-ties-fhzafeq.IQ4_XS.ggufIQ4_XS1.91GB
mergekit-ties-fhzafeq.Q4_0.ggufQ4_01.99GB
mergekit-ties-fhzafeq.IQ4_NL.ggufIQ4_NL2.0GB
mergekit-ties-fhzafeq.Q4_K_S.ggufQ4KS2.0GB
mergekit-ties-fhzafeq.Q4_K.ggufQ4_K2.09GB
mergekit-ties-fhzafeq.Q4_K_M.ggufQ4KM2.09GB
mergekit-ties-fhzafeq.Q4_1.ggufQ4_12.18GB
mergekit-ties-fhzafeq.Q5_0.ggufQ5_02.37GB
mergekit-ties-fhzafeq.Q5_K_S.ggufQ5KS2.37GB
mergekit-ties-fhzafeq.Q5_K.ggufQ5_K2.41GB
mergekit-ties-fhzafeq.Q5_K_M.ggufQ5KM2.41GB
mergekit-ties-fhzafeq.Q5_1.ggufQ5_12.55GB
mergekit-ties-fhzafeq.Q6_K.ggufQ6_K2.76GB
mergekit-ties-fhzafeq.Q8_0.ggufQ8_03.58GB

Original model description: --- base_model:

  • —Hjgugugjhuhjggg/mergekit-ties-pghuyfi
  • —Hjgugugjhuhjggg/mergekit-ties-dkhnzcn
  • —Hjgugugjhuhjggg/mergekit-ties-kmlzhzo
  • —huihui-ai/Llama-3.2-3B-Instruct-abliterated
  • —Hjgugugjhuhjggg/mergekit-ties-qgcitfu
  • —Hjgugugjhuhjggg/mergekit-ties-xflmond
  • —Hjgugugjhuhjggg/mergekit-ties-poovzrh library_name: transformers tags:
  • —mergekit
  • —merge

merge

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 huihui-ai/Llama-3.2-3B-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: Hjgugugjhuhjggg/mergekit-ties-qgcitfu
    parameters:
      density: 0.5
      weight: 0.5
  - model: Hjgugugjhuhjggg/mergekit-ties-dkhnzcn
    parameters:
      density: 0.5
      weight: 0.5
  - model: Hjgugugjhuhjggg/mergekit-ties-poovzrh
    parameters:
      density: 0.5
      weight: 0.5
  - model: Hjgugugjhuhjggg/mergekit-ties-pghuyfi
    parameters:
      density: 0.5
      weight: 0.5
  - model: Hjgugugjhuhjggg/mergekit-ties-kmlzhzo
    parameters:
      density: 0.5
      weight: 0.5
  - model: Hjgugugjhuhjggg/mergekit-ties-xflmond
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
parameters:
  normalize: false
  int8_mask: true
dtype: float16