Quantization made by Richard Erkhov.

Phi-3.5-Mini-Hyper - GGUF

Model creator: https://huggingface.co/bunnycore/
Original model: https://huggingface.co/bunnycore/Phi-3.5-Mini-Hyper/

Name	Quant method	Size
Phi-3.5-Mini-Hyper.Q2_K.gguf	Q2_K	1.32GB
Phi-3.5-Mini-Hyper.Q3_K_S.gguf	Q3_K_S	1.57GB
Phi-3.5-Mini-Hyper.Q3_K.gguf	Q3_K	1.82GB
Phi-3.5-Mini-Hyper.Q3_K_M.gguf	Q3_K_M	1.82GB
Phi-3.5-Mini-Hyper.Q3_K_L.gguf	Q3_K_L	1.94GB
Phi-3.5-Mini-Hyper.IQ4_XS.gguf	IQ4_XS	1.93GB
Phi-3.5-Mini-Hyper.Q4_0.gguf	Q4_0	2.03GB
Phi-3.5-Mini-Hyper.IQ4_NL.gguf	IQ4_NL	2.04GB
Phi-3.5-Mini-Hyper.Q4_K_S.gguf	Q4_K_S	2.04GB
Phi-3.5-Mini-Hyper.Q4_K.gguf	Q4_K	2.23GB
Phi-3.5-Mini-Hyper.Q4_K_M.gguf	Q4_K_M	2.23GB
Phi-3.5-Mini-Hyper.Q4_1.gguf	Q4_1	2.24GB
Phi-3.5-Mini-Hyper.Q5_0.gguf	Q5_0	2.46GB
Phi-3.5-Mini-Hyper.Q5_K_S.gguf	Q5_K_S	2.46GB
Phi-3.5-Mini-Hyper.Q5_K.gguf	Q5_K	2.62GB
Phi-3.5-Mini-Hyper.Q5_K_M.gguf	Q5_K_M	2.62GB
Phi-3.5-Mini-Hyper.Q5_1.gguf	Q5_1	2.68GB
Phi-3.5-Mini-Hyper.Q6_K.gguf	Q6_K	2.92GB
Phi-3.5-Mini-Hyper.Q8_0.gguf	Q8_0	3.78GB

Original model description:

base_model:

MaziyarPanahi/calme-2.1-phi3.5-4b
SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored
bunnycore/Phi-3.5-RP-Lora
SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored
nbeerbower/phi3.5-gutenberg-4B 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 Model Stock merge method using SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored 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: nbeerbower/phi3.5-gutenberg-4B
  - model: SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored+bunnycore/Phi-3.5-RP-Lora
  - model: MaziyarPanahi/calme-2.1-phi3.5-4b
merge_method: model_stock
base_model: SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored
dtype: bfloat16