Jais Family 2p7b by inceptionai

 ยป  All LLMs  ยป  inceptionai  ยป  Jais Family 2p7b   URL Share it on

  Arxiv:2307.09288   Arxiv:2308.16149   Arxiv:2402.12840   Ar   Arabic   Custom code   Decoder   En   English   Jais   Jais-family   Pytorch   Region:us   Sharded

Jais Family 2p7b Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais Family 2p7b (inceptionai/jais-family-2p7b)

Jais Family 2p7b Parameters and Internals

Model Type 
Language Model, Text Generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Chat assistants, Sentiment analysis, Document summarization
Primary Use Cases:
Arabic NLP research, Chat generation
Limitations:
Limited to Arabic and English., Cannot be used for harmful content generation.
Considerations:
Improved cultural understanding for Arabic. Not suited for other languages.
Additional Notes 
Particularly efficient at processing Arabic language contexts, aiming to cater to Arabic-speaking audiences specifically.
Supported Languages 
Arabic (High), English (High)
Training Details 
Data Sources:
Web, Code, Books, Scientific articles, Synthetic translations
Data Volume:
1.6 trillion tokens
Methodology:
Scratch pre-training and adaptation from Llama-2. Enhanced training with the SwiGLU activation function and ALiBi position encoding.
Context Length:
2048
Hardware Used:
64 Cerebras CS-2 Wafer-Scale Engines
Model Architecture:
Transformer-based, decoder-only architecture with SwiGLU for Jais-family and RoPE embedding for adapted models.
Responsible Ai Considerations 
Fairness:
Techniques implemented to reduce bias are not specified in detail.
Transparency:
Basic preprocessing and role of language-specific techniques mentioned.
Accountability:
Users are responsible for applications.
Mitigation Strategies:
Not specified in detail.
Input Output 
Input Format:
Text
Accepted Modalities:
Text
Output Format:
Generated Text
Performance Tips:
Ensure the appropriate prompt design for task adaptation.
LLM NameJais Family 2p7b
Repository ๐Ÿค—https://huggingface.co/inceptionai/jais-family-2p7b 
Required VRAM11.8 GB
Updated2024-11-04
Maintainerinceptionai
Model Typejais
Model Files  9.9 GB: 1-of-2   1.9 GB: 2-of-2
Supported Languagesar en
Gated ModelYes
Model ArchitectureJAISLMHeadModel
Licenseproprietary
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size84992
Torch Data Typefloat32
Activation Functionswiglu

Rank the Jais Family 2p7b 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  

What open-source LLMs or SLMs are you in search of? 42565 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227