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 Super by prithivMLmods

 »  All LLMs  »  prithivMLmods  »  Phi 4 Super   URL Share it on

  121   
  Merged Model   Arxiv:2403.19522   Autotrain compatible Base model:bunnycore/phi-4-rp-... Base model:lightningrodlabs/fl... Base model:mudler/localai-func... Base model:pinkstack/superthou... Base model:prithivmlmods/phi-4... Base model:prithivmlmods/phi-4... Base model:prithivmlmods/phi-4... Base model:prithivmlmods/phi-4...   Base model:unsloth/phi-4   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/prithivMLmods/Phi-4-Super 

Phi 4 Super Benchmarks

MMLU Pro: 47.4
GPQA: 19.24
MUSR: 23.28
BBH: 52.7
IFEval: 4.81 vs 88 (so35)-94.5%
MATH Lvl 5: 34.21
LLME Score: 0.38439
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 4 Super (prithivMLmods/Phi-4-Super)

Phi 4 Super Parameters and Internals

LLM NamePhi 4 Super
Repository 🤗https://huggingface.co/prithivMLmods/Phi-4-Super 
Base Model(s)  Phi 4 QwQ   Phi 4 Math IO   ...perThoughts CoT 14B 16K O1 QwQ   Phi 4 O1   bunnycore/Phi-4-RP-V0.2   Phi 4 Empathetic   LightningRodLabs/Flashlight-v1.0   mudler/LocalAI-functioncall-phi-4-v0.3   Phi 4   prithivMLmods/Phi-4-QwQ   prithivMLmods/Phi-4-Math-IO   Pinkstack/SuperThoughts-CoT-14B-16k-o1-QwQ   prithivMLmods/Phi-4-o1   bunnycore/Phi-4-RP-V0.2   prithivMLmods/Phi-4-Empathetic   LightningRodLabs/Flashlight-v1.0   mudler/LocalAI-functioncall-phi-4-v0.3   unsloth/phi-4
Merged ModelYes
Model Size14b
Required VRAM29.5 GB
Updated2025-02-05
MaintainerprithivMLmods
Model Typellama
Model Files  5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   4.9 GB: 4-of-6   5.0 GB: 5-of-6   4.6 GB: 6-of-6
Model ArchitectureLlamaForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.46.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|dummy_87|>
Vocabulary Size100352
Torch Data Typebfloat16

Best Alternatives to Phi 4 Super

Best Alternatives
Context / RAM
Downloads
Likes
...Qwen2.5llamaify 14B V23.1 200K195K / 29.7 GB51790
...Qwen2.5llamaify 14B V23.3 200K195K / 29.7 GB105
GeM2 Llamion 14B LongChat195K / 29 GB33914
Openbuddy Zero 14B V22.3 32K32K / 28 GB11601
Phi 4 ReasoningRP16K / 29.5 GB1002
GZA 14B Sce16K / 29.5 GB480
Blaze 14B XElite16K / 29.4 GB577
Phi 4 Model Stock V216K / 29.5 GB372
Phi 4 Model Stock V316K / 29.5 GB512
Phi 4 Super 116K / 29.5 GB409
Note: green Score (e.g. "73.2") means that the model is better than prithivMLmods/Phi-4-Super.

Rank the Phi 4 Super 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? 42577 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 v20241227
  Support LLM Explorer