The first open-source equivalent of OpenAI’s ChatGPT has arrived, but good luck running it. The system combines PaLM, a large language model from Google, and a technique called Reinforcement Learning with Human Feedback — RLHF. PaLM + RLHF is essentially a statistical tool to predict words.

3m read timeFrom techcrunch.com
Post cover image
2 Comments

Sort: