Model Type | |
Use Cases |
Areas: | Research, Commercial Applications |
|
Applications: | Conversational AI, Bilingual Chatbot |
|
Primary Use Cases: | Dialog Generation, Language Understanding |
|
Limitations: | Limited understanding of ultra-long documents |
|
|
Additional Notes | Improved context length, inference speed, and model efficiency. |
|
Supported Languages | Chinese (Bilingual), English (Bilingual) |
|
Training Details |
Data Sources: | |
Methodology: | Pre-training with a hybrid objective function and human preference alignment training |
|
Context Length: | |
Model Architecture: | GLM architecture with FlashAttention and Multi-Query Attention |
|
|
Input Output | |
Release Notes |
Version: | |
Notes: | Initial release with several key improvements over the first-generation model. |
|
|
|