Quantization made by Richard Erkhov.

phi-avg - GGUF

Model creator: https://huggingface.co/nell123/
Original model: https://huggingface.co/nell123/phi-avg/

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

Original model description:

base_model:

microsoft/Phi-3-mini-128k-instruct
microsoft/Phi-3-mini-4k-instruct
microsoft/Phi-3.5-mini-instruct library_name: transformers tags:
mergekit
merge

output-model-directory

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-3.5-mini-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:

models:
  - model: "microsoft/Phi-3.5-mini-instruct"
    parameters:
      weight: 1.0
  - model: "microsoft/Phi-3-mini-4k-instruct"
    parameters: 
      weight: 0.6
  - model: "microsoft/Phi-3-mini-128k-instruct"
    parameters: 
      weight: 0.3
base_model: "microsoft/Phi-3.5-mini-instruct"
merge_method: task_arithmetic
dtype: float16