Candle Phi 2 by DanielClough

 ยป  All LLMs  ยป  DanielClough  ยป  Candle Phi 2   URL Share it on

  Autotrain compatible   Custom code   Dataset:microsoft/phi-2   En   Endpoints compatible   Gguf   Phi   Q4   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Candle Phi 2 Benchmarks

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

Candle Phi 2 Parameters and Internals

Model Type 
text generation
Additional Notes 
This model is distributed in `.gguf` format for HuggingFace/Candle implementations and is not compatible with `llama.cpp`.
Supported Languages 
en (English)
LLM NameCandle Phi 2
Repository ๐Ÿค—https://huggingface.co/DanielClough/Candle_phi-2 
Model Size2.8b
Required VRAM5.6 GB
Updated2025-02-22
MaintainerDanielClough
Model Typephi
Model Files  5.6 GB   0.9 GB   1.2 GB   1.6 GB   1.7 GB   1.6 GB   1.9 GB   2.1 GB   1.9 GB   2.3 GB   3.0 GB   3.1 GB   3.2 GB   5.0 GB: 1-of-2   0.6 GB: 2-of-2
Supported Languagesen
GGUF QuantizationYes
Quantization Typeq4|gguf
Model ArchitecturePhiForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.37.0.dev0
Vocabulary Size51200
Torch Data Typefloat16

Best Alternatives to Candle Phi 2

Best Alternatives
Context / RAM
Downloads
Likes
Cinder Phi 2 V1 F16 Gguf2K / 5.6 GB1214
Cinder Phi 2 Test 12K / 11.1 GB1180
Phi 2 Lora Cfr2K / 11.1 GB190
Candle Phi 2 Old2K / 5.6 GB240
Phi2 Platypus0K / 11.1 GB50
Bnb DPO 8bit2K / 3 GB70
Phi 2 4bit 64rank2K / 5.6 GB2190
Phi 2 Instruct V12K / 11.1 GB150
Phi 2 Nf4 Fp16 Upscaled2K / 5.6 GB560
MFANN3bv0.24128K / 11.1 GB160
Note: green Score (e.g. "73.2") means that the model is better than DanielClough/Candle_phi-2.

Rank the Candle Phi 2 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? 43508 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227