chatglm3

We have hosted the application chatglm3 in order to run this application in our online workstations with Wine or directly.

Quick description about chatglm3:

ChatGLM3 is ZhipuAI & Tsinghua KEG’s third-gen conversational model suite centered on the 6B-parameter ChatGLM3-6B. It keeps the series’ smooth dialog and low deployment cost while adding native tool use (function calling), a built-in code interpreter, and agent-style workflows. The family includes base and long-context variants (8K/32K/128K). The repo ships Python APIs, CLI and web demos (Gradio/Streamlit), an OpenAI-format API server, and a compact fine-tuning kit. Quantization (4/8-bit), CPU/MPS support, and accelerator backends (TensorRT-LLM, OpenVINO, chatglm.cpp) enable lightweight local or edge deployment.

Features:

• Multi-turn chat with native tools: Function Call, Code Interpreter, agent tasks.
• Long-context models: 8K, 32K, and 128K sequence lengths.
• Easy local deployment: INT4/INT8 quantization, CPU & Apple MPS support.
• Turnkey demos: CLI, Gradio/Streamlit web UIs, OpenAI-style REST server.
• Accelerator integrations: TensorRT-LLM, OpenVINO, chatglm.cpp, multi-GPU.
• Fine-tuning kit: LoRA/QLoRA/PTuning examples and scripts.

Programming Language: Python, Unix Shell.
Categories: