Model Type | text generation, multimodal |
|
Use Cases |
Areas: | |
Applications: | Research in Arabic NLP, Development of chat assistants, Sentiment analysis, Summarization |
|
Limitations: | High-Stakes Decisions: Model should not be used without human oversight. |
|
|
Additional Notes | Techniques are extensible to other low and medium resource languages. |
|
Supported Languages | NLP (Arabic (MSA) and English) |
|
Training Details |
Data Sources: | Web, Code, Books, Scientific, Synthetic |
|
Data Volume: | |
Methodology: | |
Context Length: | |
Hardware Used: | Cerebras CS-2 Wafer-Scale Engines (WSE-2) |
|
Model Architecture: | Transformer-based, decoder-only (GPT-3) |
|
|
Responsible Ai Considerations |
Fairness: | Techniques employed to reduce bias. |
|
Accountability: | |
|
Input Output |
Input Format: | |
Output Format: | |
|