LIMA - a new 65B parameter LLaMa model fine-tuned on 1000 carefully curated prompts and responses. A few important takeaways from this work: - doesn't use RLHF - generalizes well to unseen tasks not in the training data - LIMA responses are equivalent or preferred to GPT-4 in… https://t.co/89HF3SJQnv https://t.co/ygLzmk0tZS
— elvis (@omarsar0) May 22, 2023
from Twitter https://twitter.com/omarsar0
May 22, 2023 at 07:36AM
via IFTTT
No comments:
Post a Comment