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

Jais 13B Chat by core42

 »  All LLMs  »  core42  »  Jais 13B Chat   URL Share it on

  17557   
  Arxiv:2308.16149   Ar   Arabic   Autotrain compatible   Conversational   Custom code   Decoder   En   Endpoints compatible   English   Jais   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/core42/jais-13b-chat 

Jais 13B Chat Benchmarks

LLME Score: 0.18618
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jais 13B Chat (core42/jais-13b-chat)

Jais 13B Chat Parameters and Internals

Model Type 
text generation, causal-lm, conversational
Use Cases 
Areas:
Research, Commercial Applications
Applications:
Chat-assistants, Customer Service
Primary Use Cases:
Discussion on a variety of topics, particularly Arab world
Limitations:
Should not be used for generating harmful or misleading content, Limited to Arabic and English languages
Additional Notes 
Developed as a state-of-the-art model focused on Arabic, competes well with similar-sized English models.
Supported Languages 
Arabic (High), English (High)
Training Details 
Data Sources:
Arabic prompt-response pairs, English prompt-response pairs, Curated instruction data, Translated Arabic data
Data Volume:
3.8M Arabic pairs, 5.9M English pairs
Methodology:
Instruction tuning with prompt-response pairs; masked loss on prompt during fine-tuning
Hardware Used:
Condor Galaxy 1 (CG-1) supercomputer platform
Model Architecture:
Transformer-based decoder-only (GPT-3) with SwiGLU non-linearity and ALiBi position embeddings
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Use specific prompt format for optimal performance; enable trust_remote_code=True.
LLM NameJais 13B Chat
Repository 🤗https://huggingface.co/core42/jais-13b-chat 
Model Size13b
Required VRAM53.9 GB
Updated2024-08-13
Maintainercore42
Model Typejais
Model Files  10.0 GB: 1-of-6   9.8 GB: 2-of-6   10.0 GB: 3-of-6   9.8 GB: 4-of-6   9.8 GB: 5-of-6   4.5 GB: 6-of-6
Supported Languagesar en
Model ArchitectureJAISLMHeadModel
Licenseapache-2.0
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size84992
Torch Data Typefloat32
Activation Functionswiglu

Best Alternatives to Jais 13B Chat

Best Alternatives
Context / RAM
Downloads
Likes
Jais Family 13B Chat0K / 53.9 GB45419
Jais Family 13B0K / 53.9 GB2364
Jais 13B0K / 53.9 GB8487138
Jais 13B Chat0K / 53.9 GB2061140
Jais 13B0K / 53.9 GB1401143
Note: green Score (e.g. "73.2") means that the model is better than core42/jais-13b-chat.

Rank the Jais 13B Chat 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