Re:Fine-Tuning Llama-2: A Comprehensive Case Study for Tailo...
by behnamoh on Friday August 11, 2023 @04:12PM
(#37093417)
> Its kinda like simulated annealing.
Yeah I get that. We assume there's X amount of intelligence in the LLM and try different paths to tap on that potential. The more paths are simulated, the closer we get to the LLM's intelligence asymptote. But then that's it—we can't go any further.
Yeah I get that. We assume there's X amount of intelligence in the LLM and try different paths to tap on that potential. The more paths are simulated, the closer we get to the LLM's intelligence asymptote. But then that's it—we can't go any further.