Phi-4-jackterated GGUF

Llama.cpp version: b4361

I used matteogeniaccio/phi-4 as base model and modified transformerLens to support Phi-4.

This is an experimental version, for more information about the Abliterated technique, refer to this notebook and check out @FailSpy.

Downloads last month
74
GGUF
Model size
14.7B params
Architecture
phi3
Hardware compatibility
Log In to view the estimation

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for JackCloudman/Phi-4-jackterated-GGUF

Base model

microsoft/phi-4
Quantized
(3)
this model