Jais Family 256M Chat by inceptionai

 ยป  All LLMs  ยป  inceptionai  ยป  Jais Family 256M Chat   URL Share it on

  Arxiv:2307.09288   Arxiv:2308.16149   Arxiv:2402.12840   Ar   Arabic Base model:finetune:inceptiona... Base model:inceptionai/jais-fa...   Custom code   Decoder   En   English   Jais   Jais-family   Region:us   Safetensors   Sharded   Tensorflow

Jais Family 256M Chat 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 256M Chat (inceptionai/Jais-family-256m-chat)

Jais Family 256M Chat Parameters and Internals

Model Type 
bilingual, large language model, text generation
Use Cases 
Areas:
Research, Commercial Use
Applications:
Natural language understanding and generation, Mechanistic interpretability analyses, Chat assistants, Sentiment analysis, Document summarization
Primary Use Cases:
Arabic and English language tasks
Limitations:
Handling or generating personal, confidential, or sensitive information, High-stakes decisions without human oversight
Considerations:
Model should not be used beyond its designed language proficiency or for making critical decisions without human involvement.
Additional Notes 
The model unlocks numerous use cases in Arabic NLP, with strategies extensible to other low and medium resource languages.
Supported Languages 
languages_supported (Arabic (MSA), English), proficiency (Optimized for Arabic, strong in English)
Training Details 
Data Sources:
Web, Code, Books, Scientific, Synthetic, ArXiv papers
Data Volume:
1.6 Trillion tokens
Methodology:
Instruction fine-tuned for dialog
Context Length:
16384
Hardware Used:
Cerebras CS-2 Wafer-Scale Engines
Model Architecture:
Transformer-based, decoder-only architecture, Jais models are trained from scratch, while Jais adapted models are built on Llama-2.
Safety Evaluation 
Methodologies:
Bias and misinformation assessments
Risk Categories:
Misinformation, Bias
Ethical Considerations:
Prohibits use for harmful, misleading, or inappropriate content.
Responsible Ai Considerations 
Fairness:
Efforts made to minimize biases, but biases may still be present.
Transparency:
The training and tuning processes are documented.
Accountability:
Users must ensure the model is used ethically and legally.
Mitigation Strategies:
Incorporated fine-tuning with diverse Arabic-English prompt-response pairs.
Input Output 
Input Format:
Text prompts in either Arabic or English
Accepted Modalities:
Text
Output Format:
Text generation
Performance Tips:
Model is optimized for bilingual tasks; ensure prompts are framed within supported languages.
Release Notes 
Version:
Current release
Date:
2024
Notes:
Introduction of 20 models across various sizes, featuring improved context handling and precision.
LLM NameJais Family 256M Chat
Repository ๐Ÿค—https://huggingface.co/inceptionai/Jais-family-256m-chat 
Base Model(s)  inceptionai/Jais-family-256m   inceptionai/Jais-family-256m
Model Size256m
Required VRAM1.5 GB
Updated2025-01-24
Maintainerinceptionai
Model Typejais
Model Files  1.5 GB: 1-of-1
Supported Languagesar en
Model ArchitectureJAISLMHeadModel
Licenseapache-2.0
Model Max Length2048
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size84992
Torch Data Typefloat32
Activation Functionswiglu

Rank the Jais Family 256M Chat 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? 41817 in total.

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