A very small FalconMamba-based model created by the TRL team for internal testing of training and alignment algorithms. It implements causal language modeling and includes a chat template for conversational use. Intended solely for development, debugging, and CI pipelines rather than production deployment.
Tiny FalconMambaForCausalLM is a Foundation models & chat product. It focuses on providing a minimal model for testing and debugging reinforcement learning from human feedback (RLHF) and preference optimization pipelines. It is built as an open-source project for developers. Tiny FalconMambaForCausalLM is open source under the Open Source license. It runs on the web, the command line, and API.
It is developed by TRL Internal Testing, and the product first shipped in 2024. Key capabilities include Causal LM, Test Model, and Mamba Architecture. It exposes integrations via a public API.
Latest indexed changes and source events
trl-internal-testing/tiny-FalconMambaForCausalLM verified by the PulseGate indexer
