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 sits in PulseGate's Foundation models & chat category. 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. Tiny Gemma3ForConditionalGeneration is open source under the Apache-2.0 license. Tiny Gemma3ForConditionalGeneration is available on the web, the command line, and API.
TRL Internal Testing builds and maintains Tiny Gemma3ForConditionalGeneration, and the product first shipped in 2020. Development happens publicly on GitHub with 18.9k stars and 496 commits in the last 90 days. It exposes integrations via a public API.
Latest indexed changes and source events
trl-internal-testing/tiny-Gemma3ForConditionalGeneration verified by the PulseGate indexer
Other apps tracked under the same category.
