CoolFace
Modelpublic

RichardErkhov/bunnycore_-_Phi-2-OmniMatrix-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes480downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-2-OmniMatrix - GGUF

  • —Model creator: https://huggingface.co/bunnycore/
  • —Original model: https://huggingface.co/bunnycore/Phi-2-OmniMatrix/
NameQuant methodSize
Phi-2-OmniMatrix.Q2_K.ggufQ2_K1.03GB
Phi-2-OmniMatrix.IQ3_XS.ggufIQ3_XS1.12GB
Phi-2-OmniMatrix.IQ3_S.ggufIQ3_S1.16GB
Phi-2-OmniMatrix.Q3_K_S.ggufQ3KS1.16GB
Phi-2-OmniMatrix.IQ3_M.ggufIQ3_M1.23GB
Phi-2-OmniMatrix.Q3_K.ggufQ3_K1.33GB
Phi-2-OmniMatrix.Q3_K_M.ggufQ3KM1.33GB
Phi-2-OmniMatrix.Q3_K_L.ggufQ3KL1.47GB
Phi-2-OmniMatrix.IQ4_XS.ggufIQ4_XS1.43GB
Phi-2-OmniMatrix.Q4_0.ggufQ4_01.49GB
Phi-2-OmniMatrix.IQ4_NL.ggufIQ4_NL1.5GB
Phi-2-OmniMatrix.Q4_K_S.ggufQ4KS1.51GB
Phi-2-OmniMatrix.Q4_K.ggufQ4_K1.62GB
Phi-2-OmniMatrix.Q4_K_M.ggufQ4KM1.62GB
Phi-2-OmniMatrix.Q4_1.ggufQ4_11.65GB
Phi-2-OmniMatrix.Q5_0.ggufQ5_01.8GB
Phi-2-OmniMatrix.Q5_K_S.ggufQ5KS1.8GB
Phi-2-OmniMatrix.Q5_K.ggufQ5_K1.87GB
Phi-2-OmniMatrix.Q5_K_M.ggufQ5KM1.87GB
Phi-2-OmniMatrix.Q5_1.ggufQ5_11.95GB
Phi-2-OmniMatrix.Q6_K.ggufQ6_K2.13GB
Phi-2-OmniMatrix.Q8_0.ggufQ8_02.75GB

Original model description: --- base_model:

  • —microsoft/phi-2
  • —Artples/L-MChat-Small
  • —minghaowu/phi-2-OpenHermes-2.5
  • —kingabzpro/phi-2-role-play
  • —parsak/phi-2-code-instruct
  • —l3utterfly/phi-2-layla-v1-chatml 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 task arithmetic merge method using microsoft/phi-2 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: minghaowu/phi-2-OpenHermes-2.5+kingabzpro/phi-2-role-play
    parameters:
      weight: 1.0
  - model: Artples/L-MChat-Small
    parameters:
      weight: 1.0
  - model: l3utterfly/phi-2-layla-v1-chatml
    parameters:
      weight: 1.0
  - model: parsak/phi-2-code-instruct
    parameters:
      weight: 1.0
merge_method: task_arithmetic
base_model: microsoft/phi-2
parameters:
    normalize: false
dtype: float16