GLM-130B
GLM-130B is an open bilingual pre-trained model
What is GLM-130B?
GLM-130B is a bilingual (English and Chinese) pre-trained language model with 130 billion parameters. It is designed to support inference tasks with the 130B parameters on a single server. The model uses two different mask tokens for short blank filling and left-to-right long text generation. GLM-130B is a continuation of the research on the General Language Model (GLM) and aims to provide a high-quality open-source model.
Key Features and Benefits
- Bilingual (English and Chinese).
- 130 billion parameters.
- Supports inference tasks.
- Uses two different mask tokens.
Use Cases
- Text generation.
- Language understanding.
- Natural language processing tasks.
- Pre-trained model for downstream tasks.
Loading reviews...
