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

Unaligned Thinker PHI 4 by fhai50032

 »  All LLMs  »  fhai50032  »  Unaligned Thinker PHI 4   URL Share it on

  6   
  4bit   Autotrain compatible   Conversational Dataset:fhai50032/unaligned-th...   En   Endpoints compatible   Llama   Phi-4   Phi4   Pytorch   Quantized   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/fhai50032/Unaligned-Thinker-PHI-4 

Unaligned Thinker PHI 4 Benchmarks

MMLU Pro: 46.08
GPQA: 17.45
MUSR: 18.78
BBH: 51.93
IFEval: 5.63 vs 88 (so35)-93.6%
MATH Lvl 5: 33.53
LLME Score: 0.28049
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Unaligned Thinker PHI 4 (fhai50032/Unaligned-Thinker-PHI-4)
🌟 Advertise your project 🚀

Unaligned Thinker PHI 4 Parameters and Internals

LLM NameUnaligned Thinker PHI 4
Repository 🤗https://huggingface.co/fhai50032/Unaligned-Thinker-PHI-4 
Base Model(s)  unsloth/Phi-4-unsloth-bnb-4bit   unsloth/Phi-4-unsloth-bnb-4bit
Model Size14.7b
Required VRAM29.4 GB
Updated2025-09-23
Maintainerfhai50032
Model Typellama
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.6 GB: 6-of-6   4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.6 GB: 6-of-6
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.48.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typefloat16

Best Alternatives to Unaligned Thinker PHI 4

Best Alternatives
Context / RAM
Downloads
Likes
DeepThink Phi416K / 29.4 GB241
DeepThinkers Phi416K / 29.4 GB05
Phi 4 COT16K / 29.4 GB130
Samantha2.0 Phi4 Ita 16bit16K / 29.4 GB25920
...APhi4 GRPO 250218 Merged 16bit16K / 29.4 GB100
Phi4 New Params 16bit16K / 29.4 GB60
...i4.Turn.R1Distill V1.0 Tensors16K / 29.4 GB01
Phi 4 Llama T1 Full16K / 29.4 GB41
...kpoints 511 Onlytrainex Merged31K / 29.4 GB250
...ruct Extended 3500steps Merged31K / 29.4 GB710
Note: green Score (e.g. "73.2") means that the model is better than fhai50032/Unaligned-Thinker-PHI-4.

Rank the Unaligned Thinker PHI 4 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? 51545 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