Hugging Face's logo

tensorblock
/
Phi-4-mini-instruct-abliterated-GGUF

Text Generation
Transformers
GGUF
nlp
code
abliterated
uncensored
TensorBlock
GGUF
conversational
Model card Files Community
Phi-4-mini-instruct-abliterated-GGUF / README.md
morriszms's picture
morriszms
Update README.md
910ed24 verified
preview code
|
raw
history blame contribute delete
6.71 kB
metadata
license: mit
license_link: >-
  https://huggingface.co/huihui-ai/Phi-4-mini-instruct-abliterated/resolve/main/LICENSE
language:
  - multilingual
  - ar
  - zh
  - cs
  - da
  - nl
  - en
  - fi
  - fr
  - de
  - he
  - hu
  - it
  - ja
  - ko
  - 'no'
  - pl
  - pt
  - ru
  - es
  - sv
  - th
  - tr
  - uk
pipeline_tag: text-generation
base_model: huihui-ai/Phi-4-mini-instruct-abliterated
tags:
  - nlp
  - code
  - abliterated
  - uncensored
  - TensorBlock
  - GGUF
widget:
  - messages:
      - role: user
        content: Can you provide ways to eat combinations of bananas and dragonfruits?
library_name: transformers
TensorBlock

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

huihui-ai/Phi-4-mini-instruct-abliterated - GGUF

This repo contains GGUF format model files for huihui-ai/Phi-4-mini-instruct-abliterated.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4882.

Our projects

Awesome MCP Servers TensorBlock Studio
Project A Project B
A comprehensive collection of Model Context Protocol (MCP) servers. A lightweight, open, and extensible multi-LLM interaction studio.
👀 See what we built 👀 👀 See what we built 👀
## Prompt template 
<|system|>{system_prompt}<|end|><|user|>{prompt}<|end|><|assistant|>

Model file specification

Filename Quant type File Size Description
Phi-4-mini-instruct-abliterated-Q2_K.gguf Q2_K 1.683 GB smallest, significant quality loss - not recommended for most purposes
Phi-4-mini-instruct-abliterated-Q3_K_S.gguf Q3_K_S 1.897 GB very small, high quality loss
Phi-4-mini-instruct-abliterated-Q3_K_M.gguf Q3_K_M 2.118 GB very small, high quality loss
Phi-4-mini-instruct-abliterated-Q3_K_L.gguf Q3_K_L 2.250 GB small, substantial quality loss
Phi-4-mini-instruct-abliterated-Q4_0.gguf Q4_0 2.325 GB legacy; small, very high quality loss - prefer using Q3_K_M
Phi-4-mini-instruct-abliterated-Q4_K_S.gguf Q4_K_S 2.338 GB small, greater quality loss
Phi-4-mini-instruct-abliterated-Q4_K_M.gguf Q4_K_M 2.492 GB medium, balanced quality - recommended
Phi-4-mini-instruct-abliterated-Q5_0.gguf Q5_0 2.728 GB legacy; medium, balanced quality - prefer using Q4_K_M
Phi-4-mini-instruct-abliterated-Q5_K_S.gguf Q5_K_S 2.728 GB large, low quality loss - recommended
Phi-4-mini-instruct-abliterated-Q5_K_M.gguf Q5_K_M 2.848 GB large, very low quality loss - recommended
Phi-4-mini-instruct-abliterated-Q6_K.gguf Q6_K 3.156 GB very large, extremely low quality loss
Phi-4-mini-instruct-abliterated-Q8_0.gguf Q8_0 4.085 GB very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Phi-4-mini-instruct-abliterated-GGUF --include "Phi-4-mini-instruct-abliterated-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Phi-4-mini-instruct-abliterated-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'