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

Jais Family 30B 8K by inceptionai

 »  All LLMs  »  inceptionai  »  Jais Family 30B 8K   URL Share it on

  2934   
  Arxiv:2307.09288   Arxiv:2308.16149   Arxiv:2402.12840   Ar   Arabic   Custom code   Decoder   En   English   Ext 8k   Jais   Jais-family   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/inceptionai/jais-family-30b-8k 

Jais Family 30B 8K Benchmarks

LLME Score: 0.24903
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais Family 30B 8K (inceptionai/jais-family-30b-8k)

Jais Family 30B 8K Parameters and Internals

Model Type 
bilingual, auto-regressive, transformer-based, decoder-only, LLM, causal-lm
Use Cases 
Areas:
Research, Commercial Use
Applications:
Chat assistants, Sentiment analysis, Summarization
Primary Use Cases:
Arabic NLP research, Mechanistic interpretability, Cultural analysis, Chat applications
Limitations:
Limited language proficiency outside Arabic-English
Considerations:
Avoid use in high-stakes decision making.
Supported Languages 
Arabic (MSA), English (strong)
Training Details 
Data Sources:
Web pages, Wikipedia articles, News articles, Social network content, Code data, Books, ArXiv papers, Synthetic data (in-house translation)
Data Volume:
1.6 Trillion tokens
Context Length:
16384
Model Architecture:
transformer-based, decoder-only architecture (GPT-3)
Input Output 
Input Format:
Text only data
Output Format:
Model generates text
LLM NameJais Family 30B 8K
Repository 🤗https://huggingface.co/inceptionai/jais-family-30b-8k 
Model Size30b
Required VRAM126.4 GB
Updated2025-02-05
Maintainerinceptionai
Model Typejais
Model Files  9.5 GB: 1-of-14   9.6 GB: 2-of-14   9.6 GB: 3-of-14   9.9 GB: 4-of-14   9.4 GB: 5-of-14   9.6 GB: 6-of-14   9.6 GB: 7-of-14   9.6 GB: 8-of-14   9.9 GB: 9-of-14   9.4 GB: 10-of-14   9.6 GB: 11-of-14   9.6 GB: 12-of-14   8.7 GB: 13-of-14   2.4 GB: 14-of-14
Supported Languagesar en
Context Length8k
Model ArchitectureJAISLMHeadModel
Licenseapache-2.0
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size84992
Torch Data Typefloat32
Activation Functionswiglu

Best Alternatives to Jais Family 30B 8K

Best Alternatives
Context / RAM
Downloads
Likes
Jais Family 30B 8K Chat0K / 123.6 GB2158

Rank the Jais Family 30B 8K 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