To-Do List: Difference between revisions

8 bytes removed ,  16 February 2023
no edit summary
No edit summary
No edit summary
Line 60: Line 60:


'''[[hallucinations]]''' = nonsensical answers to factual questions from large language models
'''[[hallucinations]]''' = nonsensical answers to factual questions from large language models
'''[[illustrating reinforcement learning from human feedback]] (RLHF)''' - https://huggingface.co/blog/rlhf


'''[[inference]]'''
'''[[inference]]'''
Line 98: Line 96:


'''[[replicate]]''' - use [[open-source models]] with a Cloud API, https://replicate.com/
'''[[replicate]]''' - use [[open-source models]] with a Cloud API, https://replicate.com/
'''[[RLHF]]''' - [[Reinforcement Learning from Human Feedback]] - https://huggingface.co/blog/rlhf


'''[[Transformer]]''' - https://news.ycombinator.com/item?id=34566275
'''[[Transformer]]''' - https://news.ycombinator.com/item?id=34566275