THUDM/WebGLM
WebGLM is a web-enhanced question answering system built on ChatGLM with RLHF training.
Not currently ranked — collecting fresh signals.
star history
WebGLM is an official implementation of a KDD 2023 paper that enhances large language models with web search capabilities for question answering. The system is built on ChatGLM and trained using Reinforcement Learning from Human Feedback (RLHF). It retrieves relevant web information to augment the LLM’s responses, improving factual accuracy and coverage. Models are available in 10B and 2B parameter versions on HuggingFace.
Frequently asked
- What is THUDM/WebGLM?
- WebGLM is a web-enhanced question answering system built on ChatGLM with RLHF training.
- Is WebGLM open source?
- Yes — THUDM/WebGLM is open source, released under the Apache-2.0 license.
- What language is WebGLM written in?
- THUDM/WebGLM is primarily written in Python.
- How popular is WebGLM?
- THUDM/WebGLM has 1.6k stars on GitHub.
- Where can I find WebGLM?
- THUDM/WebGLM is on GitHub at https://github.com/THUDM/WebGLM.