Ycr

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Our new work finds that approaches employing on-policy sampling or negative gradients outperform offline, maximum likelihood objectives.

Source code accompanying 'Mathematics of Epidemics on Networks' by Kiss, Miller, and Simon http://www.springer.com/us/book/9783319508047 . Documentation for the software package is at https://epidemicsonnetworks.readthedocs.io/en/latest/

No description.