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

Phi 1 5 GGUF by TKDKid1000

 »  All LLMs  »  TKDKid1000  »  Phi 1 5 GGUF   URL Share it on

  147   
  Arxiv:2309.05463   Autotrain compatible   Code   Custom code   En   Gguf   Phi-msft   Pytorch   Q2   Quantized   Region:us

Phi 1 5 GGUF Benchmarks

LLME Score: 0.17043
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Phi 1 5 GGUF Parameters and Internals

Model Type 
text generation, code generation
Use Cases 
Areas:
research
Applications:
poem writing, email drafting, story creation, text summarization, Python code generation
Limitations:
produces incorrect code snippets and statements, to be treated as suggestions, not fine-tuned for instructions, language limitations to standard English only
Considerations:
For research purposes; not suggested for direct adoption in production
Additional Notes 
Trained with selected safe data, but still vulnerable to producing harmful content.
Supported Languages 
en (standard English)
Training Details 
Data Sources:
same sources used for phi-1, with additional NLP synthetic texts
Data Volume:
150 billion tokens
Training Time:
8 days
Hardware Used:
32xA100-40G GPUs
Model Architecture:
Transformer with next-word prediction objective
Input Output 
Input Format:
QA, chat, and code formats
Accepted Modalities:
text
Output Format:
QA, chat, and code formats
Performance Tips:
Use FP16 / CUDA for optimal performance
Release Notes 
Version:
initial
Notes:
Model provides near state-of-the-art performance in language tasks for its parameter size, not fine-tuned for instructions.
LLM NamePhi 1 5 GGUF
Repository 🤗https://huggingface.co/TKDKid1000/phi-1_5-GGUF 
Required VRAM0.6 GB
Updated2024-11-22
MaintainerTKDKid1000
Model Typephi-msft
Model Files  0.6 GB   0.8 GB   0.9 GB   1.1 GB   1.2 GB   1.5 GB   2.8 GB   2.8 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Model ArchitecturePhiForCausalLM
Licenseother
Model Max Length2048
Transformers Version4.34.1
Tokenizer ClassCodeGenTokenizer
Vocabulary Size51200
Torch Data Typefloat16
Activation Functiongelu_new
Phi 1 5 GGUF (TKDKid1000/phi-1_5-GGUF)

Best Alternatives to Phi 1 5 GGUF

Best Alternatives
Context / RAM
Downloads
Likes
MFANN3bv0.7.10 GGUF2K / 1.6 GB100
Candle Phi 1 52K / 2.8 GB5280
Candle Phi 12K / 2.8 GB5090
Phi 2 GGUF2K / 1.1 GB1792
Phi 2 Quantized0K / 1.6 GB58611
Dolphin 2 6 Phi 2 Candle0K / 0 GB424
Phi 2 Hf 4bit Mlx2K / 1.8 GB25831
Phi 1 5 Q42K /  GB131
Phi1.5 Quantized 22K /  GB70
Merlin1.42K / 5.6 GB720
Note: green Score (e.g. "73.2") means that the model is better than TKDKid1000/phi-1_5-GGUF.

Rank the Phi 1 5 GGUF 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? 38200 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 v20241110
  Support LLM Explorer