ChatGLM2-6B is the second-gen Chinese-English conversational LLM from ZhipuAI/Tsinghua. It upgrades the base model with GLM’s hybrid pretraining objective, 1.4 TB bilingual data, and preference alignment—delivering big gains on MMLU, CEval, GSM8K, and BBH. The context window extends up to 32K (FlashAttention), and Multi-Query Attention improves speed and memory use. The repo includes Python APIs, CLI & web demos, OpenAI-style/FASTAPI servers, and quantized checkpoints for lightweight local deployment on GPUs or CPU/MPS.
Features
- Stronger base model: large bilingual pretrain + alignment; big benchmark lifts
- Long context variants: 8K default, 32K model (LongBench-competitive)
- Faster, lighter inference: Multi-Query Attention + FlashAttention
- Low-cost deploy: FP16/BF16, INT8/INT4 (≈5.5 GB), CPU & Apple MPS
- Demos & APIs: CLI, Gradio/Streamlit, FastAPI and OpenAI-format servers
- Finetuning & tooling: P-Tuning v2, full-parameter scripts, multi-GPU utilities
Project Samples
Categories
Large Language Models (LLM)License
Apache License V2.0Follow ChatGLM2-6B
You Might Also Like
Gen AI apps are built with MongoDB Atlas
MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of ChatGLM2-6B!