Phi3 Unlearned by MinaMila

 ยป  All LLMs  ยป  MinaMila  ยป  Phi3 Unlearned   URL Share it on

Phi3 Unlearned is an open-source language model by MinaMila. Features: 3.8b LLM, VRAM: 7.7GB, Context: 4K, Instruction-Based, LLM Explorer Score: 0.19.

  Arxiv:1910.09700   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/MinaMila/Phi3_unlearned 

Phi3 Unlearned Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi3 Unlearned (MinaMila/Phi3_unlearned)
๐ŸŒŸ Advertise your project ๐Ÿš€

Phi3 Unlearned Parameters and Internals

LLM NamePhi3 Unlearned
Repository ๐Ÿค—https://huggingface.co/MinaMila/Phi3_unlearned 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-09-23
MaintainerMinaMila
Model Typephi3
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.47.1
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Phi3 Unlearned

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3.5 Mini Instruct128K / 7.7 GB291298909
Phi 3 Mini 128K Instruct128K / 7.7 GB501941689
MediPhi Instruct128K / 7.7 GB492159
NuExtract 1.5128K / 7.7 GB116414241
Phi 3 Mini 128K Instruct128K / 7.7 GB50
NuExtract V1.5128K / 7.7 GB10851189
MediPhi Clinical128K / 7.7 GB413712
Phi 3.5 Mini TitanFusion 0.1128K / 7.7 GB50
ECE EIFFEL 3Bv2128K / 7.7 GB50
Phi 4 Mini Instruct128K / 7.7 GB362921
Note: green Score (e.g. "73.2") means that the model is better than MinaMila/Phi3_unlearned.

Rank the Phi3 Unlearned Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 52265 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a