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

Vicuna 13B V1.5 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Vicuna 13B V1.5 AWQ   URL Share it on

  5   
  Arxiv:2306.05685   Arxiv:2307.09288   4-bit   Autotrain compatible   Awq Base model:lmsys/vicuna-13b-v1... Base model:quantized:lmsys/vic...   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/vicuna-13B-v1.5-AWQ 

Vicuna 13B V1.5 AWQ Benchmarks

LLME Score: 0.12442
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Vicuna 13B V1.5 AWQ (TheBloke/vicuna-13B-v1.5-AWQ)

Vicuna 13B V1.5 AWQ Parameters and Internals

Model Type 
llama
Additional Notes 
The model uses AWQ, an efficient, accurate, and fast low-bit weight quantization, supporting 4-bit quantization. This results in faster inference and the ability to use smaller GPUs for deployment.
Training Details 
Data Sources:
ShareGPT
Methodology:
Finetuned with supervised instruction on user-shared conversations.
Context Length:
4096
Model Architecture:
Transformer
Input Output 
Input Format:
The assistant gives helpful, detailed, and polite answers to the user''s questions. USER: {prompt} ASSISTANT:
LLM NameVicuna 13B V1.5 AWQ
Repository 🤗https://huggingface.co/TheBloke/vicuna-13B-v1.5-AWQ 
Model NameVicuna 13B v1.5
Model Creatorlmsys
Base Model(s)  lmsys/vicuna-13b-v1.5   lmsys/vicuna-13b-v1.5
Model Size13b
Required VRAM7.2 GB
Updated2025-04-17
MaintainerTheBloke
Model Typellama
Model Files  7.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Vicuna 13B V1.5 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K AWQ128K / 7.2 GB32
LongAlign 13B 64K AWQ64K / 7.2 GB92
...oboros L2 13B 2 1 YaRN 64K AWQ64K / 7.2 GB162
OrcaMaid V3 13B 32K AWQ32K / 7.2 GB24
OrcaMaid V2 FIX 13B 32K AWQ32K / 7.2 GB01
NexusRaven V2 13B AWQ16K / 7.2 GB113
NexusRaven V2 13B AWQ16K / 7.2 GB43
...th CodeLlama 13B Python Hf AWQ16K / 7.5 GB60
WhiteRabbitNeo 13B AWQ16K / 7.2 GB404
NexusRaven V2 13B AWQ16K / 7.2 GB01
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/vicuna-13B-v1.5-AWQ.

Rank the Vicuna 13B V1.5 AWQ 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? 46384 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 v20241227
  Support LLM Explorer