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 6p7b by inceptionai

 »  All LLMs  »  inceptionai  »  Jais Family 6p7b   URL Share it on

  669   
  Arxiv:2307.09288   Arxiv:2308.16149   Arxiv:2402.12840   Ar   Arabic   Custom code   Decoder   En   English   Jais   Jais-family   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/inceptionai/jais-family-6p7b 

Jais Family 6p7b Benchmarks

LLME Score: 0.22963
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais Family 6p7b (inceptionai/jais-family-6p7b)

Jais Family 6p7b Parameters and Internals

Model Type 
Decoder, causal-lm, text-generation
Use Cases 
Areas:
Research, Commercial Use
Applications:
Chat assistants, Sentiment analysis, Summarization
Primary Use Cases:
Arabic NLP research, Development of chat assistants
Limitations:
Limited to Arabic and English, Potential for bias and misinformation
Considerations:
Proficiency assumed only for targeted languages.
Additional Notes 
Suitable for Arabic and English NLP. Improved context handling at extended sequence lengths.
Supported Languages 
Arabic (MSA), English (proficient)
Training Details 
Data Sources:
Web, Code, Books, Scientific, Synthetic
Data Volume:
up to 1.6 Trillion tokens
Methodology:
Instruction fine-tuned, progressive context expansion
Context Length:
16384
Hardware Used:
Condor Galaxy supercomputer, 64 Cerebras CS-2 Wafer-Scale Engines (WSE-2), 960 PetaFLOP/s
Model Architecture:
Transformer-based, decoder-only (GPT-3)
Responsible Ai Considerations 
Fairness:
Efforts made to reduce bias, but model may still exhibit bias.
Transparency:
Not explicitly stated
Accountability:
Users are responsible for generated content's use.
Mitigation Strategies:
Reduction of bias through techniques.
Input Output 
Input Format:
Text input prompts
Accepted Modalities:
text
Output Format:
Generated text output
Performance Tips:
Enable `trust_remote_code=True` for model loading.
Release Notes 
Version:
2024 release
Notes:
Includes new adaptations over Llama-2, enhanced Arabic capabilities.
LLM NameJais Family 6p7b
Repository 🤗https://huggingface.co/inceptionai/jais-family-6p7b 
Model Size7.1b
Required VRAM28.5 GB
Updated2024-11-04
Maintainerinceptionai
Model Typejais
Model Files  9.9 GB: 1-of-3   9.8 GB: 2-of-3   8.8 GB: 3-of-3
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

Best Alternatives to Jais Family 6p7b

Best Alternatives
Context / RAM
Downloads
Likes
Jais Family 6p7b Chat0K / 28.5 GB1755

Rank the Jais Family 6p7b 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