Hey HN, I've been live coding some projects this past month and here's the recent one. I'm making a ChatGPT-like React frontend for Llama 2 (deployed on the huggingface inference endpoint API)
Also wanted to show how to set up a react from scratch seeing as there's a bit of an over-reliance on bootstrapping frontends these days in education.
Enjoy! Ask me any questions about the implementation or how to fine-tune Llama 2 (have some other streams where I do that w/ LoRa/QLoRa)
Also wanted to show how to set up a react from scratch seeing as there's a bit of an over-reliance on bootstrapping frontends these days in education.
Enjoy! Ask me any questions about the implementation or how to fine-tune Llama 2 (have some other streams where I do that w/ LoRa/QLoRa)