This is a minimal randomly initialized model based on the Falcon 40B architecture. It is maintained by the optimum-intel-internal-testing organization and is used to validate compatibility and performance of the Optimum Intel toolkit without incurring the computational cost of the full 40B parameter model. The model is provided in Safetensors format.
In the Foundation models & chat space, Tiny Random Falcon 40b takes a focused approach. It focuses on testing optimization and inference pipelines for large language models at reduced scale. It is built as an open-source project for AI developers and researchers. Tiny Random Falcon 40b is open source under the Open Source license. The product ships for the web and API.
Behind Tiny Random Falcon 40b is Hugging Face, and the product first shipped in 2025.
Latest indexed changes and source events
optimum-intel-internal-testing/tiny-random-falcon-40b verified by the PulseGate indexer
Other apps tracked under the same category.
