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

Jais Adapted 7B by inceptionai

 »  All LLMs  »  inceptionai  »  Jais Adapted 7B   URL Share it on

  658   
  Arxiv:2307.09288   Arxiv:2308.16149   Arxiv:2402.12840   Ar   Arabic Base model:finetune:meta-llama... Base model:meta-llama/llama-2-...   Decoder   En   English   Jais-family   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/inceptionai/jais-adapted-7b 

Jais Adapted 7B Benchmarks

LLME Score: 0.22944
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais Adapted 7B (inceptionai/jais-adapted-7b)

Jais Adapted 7B Parameters and Internals

Model Type 
Bilingual large language model, Causal language model, Text generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Chat applications, sentiment analysis, summarization
Primary Use Cases:
Natural language understanding and generation, Chat development, Cultural analysis
Limitations:
Not suitable for non-Arabic or English languages, Not suitable for decision-making without human oversight
Considerations:
Use responsibly in compliance with legal regulations.
Additional Notes 
Optimized from Llama-2 with specialized techniques for Arabic.
Supported Languages 
Arabic (Advanced), English (Advanced)
Training Details 
Data Sources:
Web, Code, Books, Scientific papers, Synthetic translation
Data Volume:
1.6 Trillion tokens
Methodology:
From scratch and adapted pre-training methods
Context Length:
16384
Training Time:
Not specified
Hardware Used:
Cerebras CS-2 Wafer-Scale Engines
Model Architecture:
Transformer-based, decoder-only (GPT-3) with SwiGLU activation and ALiBi position encoding (Jais) / RoPE and Grouped Query Attention (adapted from Llama-2)
Safety Evaluation 
Methodologies:
GPT-4-as-a-judge evaluation
Risk Categories:
Misinformation, Bias
Ethical Considerations:
Contains disclaimers for incorrect, misleading, and/or offensive content generation.
Responsible Ai Considerations 
Fairness:
Trained on diverse datasets to reduce bias, though biases may still be present.
Transparency:
Open release of model details and license.
Accountability:
Researchers and users should ensure compliance with applicable laws.
Mitigation Strategies:
Use diverse datasets and evaluation with linguist review.
Input Output 
Input Format:
Text input
Accepted Modalities:
Text
Output Format:
Text output
Performance Tips:
Enable `trust_remote_code=True` when loading for special model classes.
Release Notes 
Version:
Initial Release
Date:
2023
Notes:
Release of the bilingual Jais family models.
LLM NameJais Adapted 7B
Repository 🤗https://huggingface.co/inceptionai/jais-adapted-7b 
Base Model(s)  Llama 2 7B   meta-llama/Llama-2-7b
Model Size7b
Required VRAM28.2 GB
Updated2024-11-04
Maintainerinceptionai
Model Typellama
Model Files  4.9 GB: 1-of-6   4.9 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   3.7 GB: 6-of-6
Supported Languagesar en
Gated ModelYes
Model ArchitectureLlamaForCausalLM
Licenseproprietary
Context Length4096
Model Max Length4096
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size64000
Torch Data Typefloat32

Best Alternatives to Jais Adapted 7B

Best Alternatives
Context / RAM
Downloads
Likes
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB531
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB49502
LlamaStock 8B128K / 16.1 GB151
SuperNeuralDreadDevil 8B128K / 16.1 GB311
Yarn Llama 2 7B 128K128K / 13.5 GB570539
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB83
LLaMA 7B PoSE Linear 96K96K / 27 GB82
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB81
Chat Llama2 7B 80K80K / 13.8 GB60
Llama2 7B 80K80K / 13.8 GB90
Note: green Score (e.g. "73.2") means that the model is better than inceptionai/jais-adapted-7b.

Rank the Jais Adapted 7B 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