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

Phi 2 4bit 64rank by LoftQ

 »  All LLMs  »  LoftQ  »  Phi 2 4bit 64rank   URL Share it on

  11   
  Arxiv:2310.08659   4bit   Autotrain compatible   Custom code   En   Endpoints compatible   Lora   Phi   Quantization   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoftQ/phi-2-4bit-64rank 

Phi 2 4bit 64rank Benchmarks

LLME Score: 0.18275
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi 2 4bit 64rank (LoftQ/phi-2-4bit-64rank)

Phi 2 4bit 64rank Parameters and Internals

LLM NamePhi 2 4bit 64rank
Repository 🤗https://huggingface.co/LoftQ/phi-2-4bit-64rank 
Model Size2.8b
Required VRAM5.6 GB
Updated2025-01-24
MaintainerLoftQ
Model Typephi
Model Files  5.0 GB: 1-of-2   0.6 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitecturePhiForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.39.3
Tokenizer ClassCodeGenTokenizer
Vocabulary Size51200
LoRA ModelYes
Torch Data Typefloat16

Best Alternatives to Phi 2 4bit 64rank

Best Alternatives
Context / RAM
Downloads
Likes
Bnb DPO 8bit2K / 3 GB930
Phi 2 Nf4 Fp16 Upscaled2K / 5.6 GB230
MFANN3bv0.24128K / 11.1 GB180
MFANN3b128K / 11.1 GB1810
MFANN3bv1.1128K / 11.1 GB420
MFANN3b SFT128K / 5.6 GB2230
MFANN3bv0.23128K / 11.1 GB90
MFANN3b Rebase128K / 11.1 GB80
MFANN3bv1.2126K / 11.1 GB280
MFANN Phigments Slerp V232K / 5.6 GB1270
Note: green Score (e.g. "73.2") means that the model is better than LoftQ/phi-2-4bit-64rank.

Rank the Phi 2 4bit 64rank 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? 41817 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