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

Vicuzard 30B Uncensored by concedo

 »  All LLMs  »  concedo  »  Vicuzard 30B Uncensored   URL Share it on

  734   
  Autotrain compatible   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded   Uncensored

Vicuzard 30B Uncensored Benchmarks

ARC: 62.97 vs 96.7 (so35)-34.9%
HellaSwag: 83.68 vs 95.3 (gpt4)-12.2%
MMLU: 58.16 vs 88.3 (so35)-34.1%
TruthfulQA: 52.27 vs 59 (gpt4)-11.4%
WinoGrande: 77.11 vs 87.5 (gpt4)-11.9%
GSM8K: 15.39 vs 96.4 (so35)-84%
LLME Score: 0.1608
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Vicuzard 30B Uncensored Parameters and Internals

LLM NameVicuzard 30B Uncensored
Repository 🤗https://huggingface.co/concedo/Vicuzard-30B-Uncensored 
Model Size30b
Required VRAM64.9 GB
Updated2024-09-19
Maintainerconcedo
Model Typellama
Model Files  6.1 GB: 1-of-11   6.2 GB: 2-of-11   6.2 GB: 3-of-11   6.2 GB: 4-of-11   6.2 GB: 5-of-11   6.2 GB: 6-of-11   6.2 GB: 7-of-11   6.2 GB: 8-of-11   6.2 GB: 9-of-11   6.2 GB: 10-of-11   3.0 GB: 11-of-11
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.29.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat16
Vicuzard 30B Uncensored (concedo/Vicuzard-30B-Uncensored)

Best Alternatives to Vicuzard 30B Uncensored

Best Alternatives
Context / RAM
Downloads
Likes
...nsored Instruct PL Lora Unload2K / 65.2 GB6910
Wizard Vicuna 30B Uncensored2K / 130.5 GB2377138
...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 concedo/Vicuzard-30B-Uncensored.

Rank the Vicuzard 30B Uncensored 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? 36073 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 v2024072803
  Support LLM Explorer