File size: 732 Bytes
f077d69 9059d91 | 1 2 3 4 5 6 7 8 | ---
license: cc-by-nd-4.0
datasets:
- starhopp3r/TinyChat
language:
- en
---
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](https://nikhilr.io/posts/TinyChat15M/). |