LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Vicuna 33B 1 3 SuperHOT 8K GPTQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18857 in total.

 ยป  All LLMs  ยป  TheBloke  ยป  Vicuna 33B 1 3 SuperHOT 8K GPTQ   URL Share it on

  Arxiv:2302.13971   Arxiv:2306.05685   4-bit   Autotrain compatible   Custom code   Ext 8k   Gptq   License:other   Llama   Quantized   Region:us   Safetensors

Rank the Vicuna 33B 1 3 SuperHOT 8K GPTQ 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  
Vicuna 33B 1 3 SuperHOT 8K GPTQ (TheBloke/Vicuna-33B-1-3-SuperHOT-8K-GPTQ)

Best Alternatives to Vicuna 33B 1 3 SuperHOT 8K GPTQ

Best Alternatives
HF Rank
Zephyrus L1 33B60.612K / 50.6 GB24254
...t 6 Llama 33B Xor MERGED 16bit60.452K / 65.2 GB24012
WizardLM 33B V1.0 Uncensored59.992K / 65.2 GB206658
Fin Llama 33B Merged59.332K / 65.2 GB213814
Samantha 1.1 Llama 33B58.982K / 65.2 GB107016
Chronoboros 33B58.922K / 65.1 GB26669
Scarlett 33B58.812K / 65.3 GB227123
Airochronos 33B58.752K / 65.1 GB26636
Vicuna 33B V1.358.542K / 65.2 GB10993273
Uncensored Frank 33B58.382K / 65.3 GB26975
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Vicuna-33B-1-3-SuperHOT-8K-GPTQ.

Vicuna 33B 1 3 SuperHOT 8K GPTQ Parameters and Internals

LLM NameVicuna 33B 1 3 SuperHOT 8K GPTQ
RepositoryOpen on ๐Ÿค— 
Model Size33b
Required VRAM16.9 GB
Model Typellama
Model Files  16.9 GB
GPTQ QuantizationYes
Context Length8k
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003