Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
7.67k
stars
668
forks
source link
Noob question: How can I use this model for inference? #8
Closed
PrasoonPratham closed 1 year ago
@PrasoonPratham There are currently no provided pre-trained weights. This is just the complete architecture to pre-train your own models.