Phizzle by Isotonic

 ยป  All LLMs  ยป  Isotonic  ยป  Phizzle   URL Share it on

  Merged Model   Autotrain compatible Cognitivecomputations/dolphin-...   Custom code   Endpoints compatible   Mrm8488/phi-2-coder   Phi-msft   Region:us   Rhysjones/phi-2-orange   Safetensors   Sharded   Tensorflow

Phizzle Benchmarks

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

Phizzle Parameters and Internals

Model Type
merge
Additional NotesPhizzle is a merge of the following models using LazyMergekit: rhysjones/phi-2-orange, cognitivecomputations/dolphin-2_6-phi-2, mrm8488/phi-2-coder.
Training Details
Data Sources:
rhysjones/phi-2-orange, cognitivecomputations/dolphin-2_6-phi-2, mrm8488/phi-2-coder
Methodology:ties, LazyMergekit
LLM NamePhizzle
Repository ๐Ÿค—https://huggingface.co/Isotonic/phizzle 
Merged ModelYes
Model Size2.8b
Required VRAM5.6 GB
Updated2024-11-09
MaintainerIsotonic
Model Typephi-msft
Model Files  2.0 GB: 1-of-3   2.0 GB: 2-of-3   1.6 GB: 3-of-3
Model ArchitecturePhiForCausalLM
Licenseapache-2.0
Model Max Length2048
Transformers Version4.36.2
Tokenizer ClassCodeGenTokenizer
Padding Token<|endoftext|>
Vocabulary Size51200
Torch Data Typefloat16
Activation Functiongelu_new
Phizzle (Isotonic/phizzle)

Best Alternatives to Phizzle

Best Alternatives
Context / RAM
Downloads
Likes
MFANN3bv0.23128K / 11.1 GB280
MFANN Phigments Slerp V232K / 5.6 GB19090
MFANN3bv0.2232K / 11.1 GB390
MFANN3bv0.2132K / 11.1 GB90
MFANN3bv0.20.1632K / 5.6 GB3710
MFANN3bv0.1932K / 11.1 GB100
MFANN3bv0.1832K / 11.1 GB150
MFANN3bv0.19.1232K / 5.6 GB3750
MFANN3bv0.1532K / 11.1 GB120
MFANN Phigments12 Slerp32K / 5.6 GB280
Note: green Score (e.g. "73.2") means that the model is better than Isotonic/phizzle.

Rank the Phizzle 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? 37688 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110