Wizard Vicuna 30B Uncensored by ehartford

 ยป  All LLMs  ยป  ehartford  ยป  Wizard Vicuna 30B Uncensored   URL Share it on

  Autotrain compatible Dataset:ehartford/wizard vicun...   En   Endpoints compatible   Llama   Model-index   Pytorch   Region:us   Sharded   Uncensored

Wizard Vicuna 30B Uncensored Benchmarks

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

Wizard Vicuna 30B Uncensored Parameters and Internals

LLM NameWizard Vicuna 30B Uncensored
Repository ๐Ÿค—https://huggingface.co/cognitivecomputations/Wizard-Vicuna-30B-Uncensored 
Model Size30b
Required VRAM130.5 GB
Updated2024-09-19
Maintainerehartford
Model Typellama
Model Files  9.9 GB: 1-of-14   9.7 GB: 2-of-14   9.8 GB: 3-of-14   10.0 GB: 4-of-14   9.8 GB: 5-of-14   9.9 GB: 6-of-14   9.9 GB: 7-of-14   9.8 GB: 8-of-14   10.0 GB: 9-of-14   9.8 GB: 10-of-14   9.9 GB: 11-of-14   9.9 GB: 12-of-14   9.8 GB: 13-of-14   2.3 GB: 14-of-14   0.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32
Wizard Vicuna 30B Uncensored (cognitivecomputations/Wizard-Vicuna-30B-Uncensored)

Quantized Models of the Wizard Vicuna 30B Uncensored

Model
Likes
Downloads
VRAM
...ard Vicuna 30B Uncensored Fp161772365 GB

Best Alternatives to Wizard Vicuna 30B Uncensored

Best Alternatives
Context / RAM
Downloads
Likes
...nsored Instruct PL Lora Unload2K / 65.2 GB6910
Vicuzard 30B Uncensored2K / 64.9 GB73411
...ored SuperCOT StoryTelling 30B2K / 65.2 GB138745
WizardLM 30B Uncensored2K / 65.2 GB734138
...ncensored Guanaco SuperCOT 30B2K / 65.2 GB69624
...ardLM OpenAssistant 30B Native2K / 64.1 GB6840
...T StoryTelling 30B SuperHOT 8K2K / 65.2 GB62
Flash Llama 30M 2000132K / 0.1 GB7020
Smaug Slerp 30B V0.132K / 60.4 GB610
Llama33b 16K16K / 65.2 GB61
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/Wizard-Vicuna-30B-Uncensored.

Rank the Wizard Vicuna 30B Uncensored 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? 36073 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803