Phi 2 GGUF by second-state

 ยป  All LLMs  ยป  second-state  ยป  Phi 2 GGUF   URL Share it on

  Autotrain compatible   Base model:microsoft/phi-2 Base model:quantized:microsoft...   Code   Custom code   En   Gguf   Phi   Q2   Quantized   Region:us
Model Card on HF ๐Ÿค—: https://huggingface.co/second-state/phi-2-GGUF 

Phi 2 GGUF Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 2 GGUF (second-state/phi-2-GGUF)

Phi 2 GGUF Parameters and Internals

Model Type 
phi-msft
Supported Languages 
en (high)
LLM NamePhi 2 GGUF
Repository ๐Ÿค—https://huggingface.co/second-state/phi-2-GGUF 
Model NamePhi 2
Model CreatorMicrosoft
Base Model(s)  Phi 2   microsoft/phi-2
Required VRAM1.1 GB
Updated2024-12-22
Maintainersecond-state
Model Typephi-msft
Model Files  1.1 GB   1.6 GB   1.4 GB   1.2 GB   1.6 GB   1.7 GB   1.6 GB   1.9 GB   2.0 GB   1.9 GB   2.3 GB   3.0 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Model ArchitecturePhiForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.37.0
Vocabulary Size51200
Torch Data Typefloat16

Best Alternatives to Phi 2 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
MFANN3bv0.7.10 GGUF2K / 1.6 GB50
Candle Phi 1 52K / 2.8 GB4310
Candle Phi 12K / 2.8 GB4270
Phi 2 Quantized0K / 1.6 GB42311
Phi 1 5 GGUF0K / 0.6 GB1126
Dolphin 2 6 Phi 2 Candle0K / 0 GB274
Phi 2 Hf 4bit Mlx2K / 1.8 GB14841
Phi 1 5 Q42K /  GB71
Phi1.5 Quantized 22K /  GB90
Merlin1.42K / 5.6 GB680
Note: green Score (e.g. "73.2") means that the model is better than second-state/phi-2-GGUF.

Rank the Phi 2 GGUF 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217