This is a very small, toy-sized version of a Gemma3 model created specifically for internal testing of the TRL (Transformers Reinforcement Learning) library. It implements conditional text generation with a custom chat template. It is not intended for real-world usage but serves as a minimal reproducible example for library development.
Tiny Gemma3ForConditionalGeneration is a Foundation models & chat project. It focuses on providing a minimal model for testing conditional generation features in the TRL library. It is built as an open-source project for machine learning library developers and testers. The project is open source (Apache-2.0). It ships for the web, the command line, and API.
Behind Tiny Gemma3ForConditionalGeneration is TRL Internal Testing, and it first shipped in 2020. The project is developed in the open on GitHub with 18.9k stars and 496 commits in the last 90 days. It exposes integrations via a public API.
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