Running the ChatGLM-6B model in OpenBayes

ChatGLM-6B model

 ChatGLM-6B is an open source, bilingual conversational language model that supports both Chinese and English. It is based on the general language model (GLM) architecture and has 6.2 billion parameters. Combined with model quantization technology, users can perform local (INT4 quantization) on consumer-grade graphics cards with as little as 6 GB of video memory). ChatGLM-6B uses similar technology to ChatGPT and is optimized for Chinese question-answering and conversation. After bilingual training in Chinese and English with about 1T of identifiers, supplemented by supervision, self-feedback, human feedback reinforcement learning and other technologies, the 6.2 billion parameter ChatGLM-6B can already generate answers that are quite in line with human preferences.

Rapid deployment

1. Open a new terminal page

2. Enter the command cd ChatGLM-6B  Switch to directory ChatGLM-6B

3. Enter the command python web_demo.py  Press Enter to run the Gradio demo. This process may take a few seconds.

4. After http://0.0.0.0:8080 appears, open the API address to access (real-name authentication is required to access the API address)

5. Open the API address and you can use ChatGLM-6B