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

Jais 13B by inceptionai

 »  All LLMs  »  inceptionai  »  Jais 13B   URL Share it on

  1401   
  Arxiv:2308.16149   Ar   Arabic   Autotrain compatible   Custom code   Decoder   En   English   Jais   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/inceptionai/jais-13b 

Jais 13B Benchmarks

LLME Score: 0.15262
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais 13B (inceptionai/jais-13b)

Jais 13B Parameters and Internals

Model Type 
text generation, causal-lm
Use Cases 
Areas:
Research, Commercial Use
Applications:
Chat-assistants, Customer service
Limitations:
The model should not be used for generating harmful, misleading, or inappropriate content., Should not handle or generate personal, confidential, or sensitive information., Not for generalization across all languages.
Additional Notes 
Jais-13b is a powerful bilingual model, carefully built, but aware of potential biases and misuse.
Supported Languages 
Arabic (Bilingual model supports Arabic), English (Bilingual model supports English)
Training Details 
Data Sources:
web pages, wikipedia articles, news articles, Arabic books, social network content
Data Volume:
72 billion Arabic tokens, 279 billion English/code tokens
Methodology:
Transformer-based decoder-only architecture with SwiGLU non-linearity and ALiBi position embeddings
Hardware Used:
Condor Galaxy 1 (CG-1) supercomputer platform
Model Architecture:
Transformer-based decoder-only (GPT-3)
Responsible Ai Considerations 
Mitigation Strategies:
Techniques applied to reduce bias, ongoing feedback and research welcome.
Input Output 
Input Format:
Text only data.
Output Format:
Model generates text.
LLM NameJais 13B
Repository 🤗https://huggingface.co/inceptionai/jais-13b 
Model Size13b
Required VRAM53.9 GB
Updated2024-11-13
Maintainerinceptionai
Model Typejais
Model Files  10.0 GB: 1-of-6   9.8 GB: 2-of-6   10.0 GB: 3-of-6   9.8 GB: 4-of-6   9.8 GB: 5-of-6   4.5 GB: 6-of-6
Supported Languagesar en
Gated ModelYes
Model ArchitectureJAISLMHeadModel
Licenseproprietary
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size84992
Torch Data Typefloat32
Activation Functionswiglu

Best Alternatives to Jais 13B

Best Alternatives
Context / RAM
Downloads
Likes
Jais Family 13B Chat0K / 53.9 GB45419
Jais Family 13B0K / 53.9 GB2364
Jais 13B Chat0K / 53.9 GB17557134
Jais 13B0K / 53.9 GB8487138
Jais 13B Chat0K / 53.9 GB2061140
Note: green Score (e.g. "73.2") means that the model is better than inceptionai/jais-13b.

Rank the Jais 13B 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? 42577 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