Download
ChatGLM-6B is an open bilingual (Chinese + English) conversational language model based on the GLM architecture, with approximately 6.2 billion parameters. The project provides inference code, demos (command line, web, API), quantization support for lower memory deployment, and tools for finetuning (e.g., via P-Tuning v2). It is optimized for dialogue and question answering with a balance between performance and deployability in consumer hardware settings. Support for quantized inference (INT4, INT8) to reduce GPU memory requirements. Automatic mode switching between precision/memory tradeoffs (full/quantized).
Features
- Bilingual dialogue capability (Chinese and English)
- Support for quantized inference (INT4, INT8) to reduce GPU memory requirements
- Parameter-efficient finetuning (P-Tuning v2 method)
- CLI, web demo, and API interfaces included
- Automatic mode switching between precision / memory tradeoffs (full / quantized)
- Integration with the Hugging Face / Transformers ecosystem (trust_remote_code, model loading, tokenization)
Project Samples
License
Apache License V2.0Follow ChatGLM-6B
Other Useful Business Software
Dragonfly | An In-Memory Data Store without Limits
Dragonfly is a drop-in Redis replacement that is designed for heavy data workloads running on modern cloud hardware. Migrate in less than a day and experience up to 25X the performance on half the infrastructure.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of ChatGLM-6B!
