CoolFace
Modelpublic

RichardErkhov/bunnycore_-_Phi-3.5-Hyper-Mix-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes269downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-3.5-Hyper-Mix - GGUF

  • —Model creator: https://huggingface.co/bunnycore/
  • —Original model: https://huggingface.co/bunnycore/Phi-3.5-Hyper-Mix/
NameQuant methodSize
Phi-3.5-Hyper-Mix.Q2_K.ggufQ2_K1.32GB
Phi-3.5-Hyper-Mix.IQ3_XS.ggufIQ3_XS1.51GB
Phi-3.5-Hyper-Mix.IQ3_S.ggufIQ3_S1.57GB
Phi-3.5-Hyper-Mix.Q3_K_S.ggufQ3KS1.57GB
Phi-3.5-Hyper-Mix.IQ3_M.ggufIQ3_M1.73GB
Phi-3.5-Hyper-Mix.Q3_K.ggufQ3_K1.82GB
Phi-3.5-Hyper-Mix.Q3_K_M.ggufQ3KM1.82GB
Phi-3.5-Hyper-Mix.Q3_K_L.ggufQ3KL1.94GB
Phi-3.5-Hyper-Mix.IQ4_XS.ggufIQ4_XS1.93GB
Phi-3.5-Hyper-Mix.Q4_0.ggufQ4_02.03GB
Phi-3.5-Hyper-Mix.IQ4_NL.ggufIQ4_NL2.04GB
Phi-3.5-Hyper-Mix.Q4_K_S.ggufQ4KS2.04GB
Phi-3.5-Hyper-Mix.Q4_K.ggufQ4_K2.23GB
Phi-3.5-Hyper-Mix.Q4_K_M.ggufQ4KM2.23GB
Phi-3.5-Hyper-Mix.Q4_1.ggufQ4_12.24GB
Phi-3.5-Hyper-Mix.Q5_0.ggufQ5_02.46GB
Phi-3.5-Hyper-Mix.Q5_K_S.ggufQ5KS2.46GB
Phi-3.5-Hyper-Mix.Q5_K.ggufQ5_K2.62GB
Phi-3.5-Hyper-Mix.Q5_K_M.ggufQ5KM2.62GB
Phi-3.5-Hyper-Mix.Q5_1.ggufQ5_12.68GB
Phi-3.5-Hyper-Mix.Q6_K.ggufQ6_K2.92GB
Phi-3.5-Hyper-Mix.Q8_0.ggufQ8_03.78GB

Original model description: --- base_model:

  • —ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
  • —bunnycore/Phi-3.5-mini-System-lora
  • —nbeerbower/phi3.5-gutenberg-4B
  • —bunnycore/Phi-3.1-EvolKit-lora
  • —ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
  • —nbeerbower/phi3.5-gutenberg-4B
  • —bunnycore/Phi-3.5-Mini-RP-Sonet
  • —AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding
  • —bunnycore/Phi-3.1-EvolKit-lora 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 ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1 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: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1+bunnycore/Phi-3.5-mini-System-lora
    parameters:
      density: 0.5
      weight: 0.5
  - model: nbeerbower/phi3.5-gutenberg-4B+bunnycore/Phi-3.5-Mini-RP-Sonet
    parameters:
      density: 0.5
      weight: 0.5
  - model: AXCXEPT/Borea-Phi-3.5-mini-Instruct-Coding+bunnycore/Phi-3.1-EvolKit-lora
    parameters:
      density: 0.5
      weight: 0.5
  - model: nbeerbower/phi3.5-gutenberg-4B+bunnycore/Phi-3.1-EvolKit-lora
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
parameters:
  normalize: false
  int8_mask: true
dtype: float16