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

Wizard Vicuna 13B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Wizard Vicuna 13B GPTQ   URL Share it on

  29   
  4-bit   Autotrain compatible Base model:junelee/wizard-vicu... Base model:quantized:junelee/w...   En   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/wizard-vicuna-13B-GPTQ 

Wizard Vicuna 13B GPTQ Benchmarks

ARC: 28.67 vs 96.7 (so35)-70.4%
HellaSwag: 25.94 vs 95.3 (gpt4)-72.8%
MMLU: 25.84 vs 88.3 (so35)-70.7%
TruthfulQA: 48.53 vs 59 (gpt4)-17.7%
WinoGrande: 74.74 vs 87.5 (gpt4)-14.6%
GSM8K: 9.63 vs 96.4 (so35)-90%
LLME Score: 0.13246
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Wizard Vicuna 13B GPTQ (TheBloke/wizard-vicuna-13B-GPTQ)
🌟 Advertise your project 🚀

Wizard Vicuna 13B GPTQ Parameters and Internals

Model Type 
causal-lm, llama
Additional Notes 
The model leverages both WizardLM and VicunaLM techniques, focusing on handling datasets and multi-round conversation capabilities.
Training Details 
Data Sources:
https://huggingface.co/datasets/junelee/wizard_vicuna_70k
Methodology:
Combined WizardLM and VicunaLM techniques to handle datasets and multi-round conversations.
Training Time:
35 hours
Hardware Used:
8 A100 GPUs
LLM NameWizard Vicuna 13B GPTQ
Repository 🤗https://huggingface.co/TheBloke/wizard-vicuna-13B-GPTQ 
Model NameWizard Vicuna 13B
Model Creatorjunelee
Base Model(s)  Wizard Vicuna 13B   junelee/wizard-vicuna-13b
Model Size13b
Required VRAM7.3 GB
Updated2025-08-19
MaintainerTheBloke
Model Typellama
Model Files  7.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
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

Best Alternatives to Wizard Vicuna 13B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB1116
LongAlign 13B 64K GPTQ64K / 7.3 GB41
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB93
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB121
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB103
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB74
EverythingLM 13B 16K GPTQ16K / 7.3 GB1613
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB81
Tinybra 13B GPTQ 4BIT16K / 7 GB60
LlongOrca 13B 16K GPT16K / 7.3 GB60
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/wizard-vicuna-13B-GPTQ.

Rank the Wizard Vicuna 13B GPTQ 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? 50751 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 v20241124
  Support LLM Explorer