TinyChat15M is a 15-million parameter conversational language model built on the Meta Llama 2 architecture. Designed to operate on devices with as little as 60 MB of free memory, TinyChat15M has been successfully deployed on the Sipeed LicheeRV Nano W, a compact RISC-V development board equipped with just 256 MB of DDR3 memory. Inspired by Dr. Andrej Karpathy’s llama2.c project, TinyChat15M showcases that small conversational language models can be both effective and resource-efficient, making advanced AI capabilities more accessible and sustainable. You can find a detailed blog post on this project here.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.