This is a tiny random-weight model based on the GLM-4 architecture, published for internal testing by the Optimum Intel team. It includes support for tool calling, system prompts, and a complex chat template. The model is used to validate export, quantization, and inference pipelines.
Tiny Random Glm4 is a Foundation models & chat project. It focuses on testing integration, optimization, and tool-calling capabilities for the GLM-4 model architecture. It is built as an open-source project for developers. The project is open source (Open Source). It ships for the web and API.
Behind Tiny Random Glm4 is optimum-intel-internal-testing. Among its 4 catalogued features are Test Model, GLM-4, and Chat Template.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do