Jais Adapted 7B Chat by inceptionai

 ยป  All LLMs  ยป  inceptionai  ยป  Jais Adapted 7B Chat   URL Share it on

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

Jais Adapted 7B Chat Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
๐ŸŒŸ Advertise your project ๐Ÿš€

Jais Adapted 7B Chat Parameters and Internals

Model Type 
text generation, bilingual LLM, causal-lm
Use Cases 
Areas:
Research, Commercial applications
Applications:
Natural language understanding, Generation tasks, Chat assistants, Sentiment analysis, Summarization
Primary Use Cases:
General AI assistant for Arabic and English, Cultural aligned language processing
Limitations:
Not suitable for multipurpose languages, Requires responsible use avoiding prohibited applications., Has limitations in handling non-target languages
Considerations:
Model should be used with understanding of its capability in Arabic and English. Not suitable for high-stakes decisions without human oversight.
Additional Notes 
Extensive release focuses on Arabic NLP, model adaptation, and providing bilingual capabilities.
Supported Languages 
languages_supported (Arabic, English), proficiency_level (High)
Training Details 
Data Sources:
Web pages, Wikipedia articles, News articles, Social network content, Code data, Books, Scientific papers, Synthetic translation
Data Volume:
1.6 Trillion tokens
Methodology:
Pre-training from scratch and adaptive pre-training from Llama-2
Context Length:
16384
Hardware Used:
Condor Galaxy Supercomputer, 64 Cerebras CS-2 Wafer-Scale Engines
Model Architecture:
Auto-regressive transformer-based, decoder-only (GPT-3) with SwiGLU and ALiBi or RoPE and Grouped Query Attention
Safety Evaluation 
Risk Categories:
Misinformation, Bias
Ethical Considerations:
Efforts to reduce bias; model may still exhibit biases and generate incorrect or misleading content.
Responsible Ai Considerations 
Fairness:
Techniques employed to reduce bias
Accountability:
User is responsible for model usage and outcomes
Mitigation Strategies:
Training data curated by Inception and includes techniques to minimize bias.
Input Output 
Input Format:
Text input
Accepted Modalities:
Text
Output Format:
Generates text
LLM NameJais Adapted 7B Chat
Repository ๐Ÿค—https://huggingface.co/inceptionai/jais-adapted-7b-chat 
Base Model(s)  Jais Adapted 7B   inceptionai/jais-adapted-7b
Model Size7b
Required VRAM28 GB
Updated2024-11-04
Maintainerinceptionai
Model Typellama
Model Files  9.9 GB: 1-of-3   10.0 GB: 2-of-3   8.1 GB: 3-of-3
Supported Languagesar en
Gated ModelYes
Model ArchitectureLlamaForCausalLM
Licenseproprietary
Context Length4096
Model Max Length4096
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size64000
Torch Data Typefloat32
Jais Adapted 7B Chat (inceptionai/jais-adapted-7b-chat)

Best Alternatives to Jais Adapted 7B Chat

Best Alternatives
Context / RAM
Downloads
Likes
A6 L1024K / 16.1 GB2010
M1024K / 16.1 GB1270
1571024K / 16.1 GB1010
A3.41024K / 16.1 GB130
1241024K / 16.1 GB930
A5.41024K / 16.1 GB120
A2.41024K / 16.1 GB120
2 Very Sci Fi1024K / 16.1 GB3170
1621024K / 16.1 GB600
1181024K / 16.1 GB150
Note: green Score (e.g. "73.2") means that the model is better than inceptionai/jais-adapted-7b-chat.

Rank the Jais Adapted 7B 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? 48046 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124