You can deploy this model and start earning money today!

RichardErkhov/
mergekit-community_-_mergekit-ties-rsmvina-gguf

Name: mergekit-community_-_mergekit-ties-rsmvina-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

mergekit-ties-rsmvina - GGUF

Model creator: https://huggingface.co/mergekit-community/
Original model: https://huggingface.co/mergekit-community/mergekit-ties-rsmvina/

Name	Quant method	Size
mergekit-ties-rsmvina.Q2_K.gguf	Q2_K	1.32GB
mergekit-ties-rsmvina.IQ3_XS.gguf	IQ3_XS	1.51GB
mergekit-ties-rsmvina.IQ3_S.gguf	IQ3_S	1.57GB
mergekit-ties-rsmvina.Q3_K_S.gguf	Q3_K_S	1.57GB
mergekit-ties-rsmvina.IQ3_M.gguf	IQ3_M	1.73GB
mergekit-ties-rsmvina.Q3_K.gguf	Q3_K	1.82GB
mergekit-ties-rsmvina.Q3_K_M.gguf	Q3_K_M	1.82GB
mergekit-ties-rsmvina.Q3_K_L.gguf	Q3_K_L	1.94GB
mergekit-ties-rsmvina.IQ4_XS.gguf	IQ4_XS	1.93GB
mergekit-ties-rsmvina.Q4_0.gguf	Q4_0	2.03GB
mergekit-ties-rsmvina.IQ4_NL.gguf	IQ4_NL	2.04GB
mergekit-ties-rsmvina.Q4_K_S.gguf	Q4_K_S	2.04GB
mergekit-ties-rsmvina.Q4_K.gguf	Q4_K	2.23GB
mergekit-ties-rsmvina.Q4_K_M.gguf	Q4_K_M	2.23GB
mergekit-ties-rsmvina.Q4_1.gguf	Q4_1	2.24GB
mergekit-ties-rsmvina.Q5_0.gguf	Q5_0	2.46GB
mergekit-ties-rsmvina.Q5_K_S.gguf	Q5_K_S	2.46GB
mergekit-ties-rsmvina.Q5_K.gguf	Q5_K	2.62GB
mergekit-ties-rsmvina.Q5_K_M.gguf	Q5_K_M	2.62GB
mergekit-ties-rsmvina.Q5_1.gguf	Q5_1	2.68GB
mergekit-ties-rsmvina.Q6_K.gguf	Q6_K	2.92GB
mergekit-ties-rsmvina.Q8_0.gguf	Q8_0	3.78GB

Original model description:

base_model:

microsoft/Phi-3-mini-128k-instruct 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 microsoft/Phi-3-mini-128k-instruct 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: microsoft/Phi-3-mini-128k-instruct
    parameters:
      density: 0.5
      weight: 0.5
  - model: microsoft/Phi-3-mini-128k-instruct
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: microsoft/Phi-3-mini-128k-instruct
parameters:
  normalize: false
  int8_mask: true
dtype: float16

RichardErkhov/mergekit-community_-_mergekit-ties-rsmvina-gguf