LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Phi 4 Abliterated by Orion-zhen

 »  All LLMs  »  Orion-zhen  »  Phi 4 Abliterated   URL Share it on

  44   
Base model:finetune:microsoft/...   Base model:microsoft/phi-4   Conversational   Custom code   En   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Orion-zhen/phi-4-abliterated 

Phi 4 Abliterated Benchmarks

MMLU Pro: 47.69
GPQA: 20.58
MUSR: 23.18
BBH: 52.46
IFEval: 5.76 vs 88 (so35)-93.5%
MATH Lvl 5: 30.21
LLME Score: 0.28844
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 Abliterated (Orion-zhen/phi-4-abliterated)
🌟 Advertise your project 🚀

Phi 4 Abliterated Parameters and Internals

LLM NamePhi 4 Abliterated
Repository 🤗https://huggingface.co/Orion-zhen/phi-4-abliterated 
Base Model(s)  Phi 4   microsoft/phi-4
Model Size14.7b
Required VRAM29.4 GB
Updated2025-09-24
MaintainerOrion-zhen
Model Typephi3
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.8 GB: 4-of-6   4.8 GB: 5-of-6   5.0 GB: 6-of-6
Supported Languagesen
Model ArchitecturePhi3ForCausalLM
Licensegpl-3.0
Context Length16384
Model Max Length16384
Transformers Version4.47.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Reasoning32K / 29.4 GB242261204
Phi 4 Reasoning Plus32K / 29.4 GB12750323
Phi 4 Reasoning Plus32K / 29.4 GB11814
Phi 416K / 29.4 GB13130692161
Flashlight V1.116K / 29.4 GB50
Microsoft Phi 416K / 29.4 GB110055
Phi 4 RP V016K / 29.5 GB83
Phi4 Abliterated16K / 29.4 GB712
Phi 4 AbliteratedRP16K / 29.5 GB65
DNA R116K / 29.4 GB105739
Note: green Score (e.g. "73.2") means that the model is better than Orion-zhen/phi-4-abliterated.

Rank the Phi 4 Abliterated Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51544 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer