Hacker News with Generative AI: Fine-Tuning

All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning (arxiv.org)
From a first-principles perspective, it may seem odd that the strongest results in foundation model fine-tuning (FT) are achieved via a relatively complex, two-stage training procedure.
Machine Learning, Reinforcement Learning, Fine-Tuning, Foundation Models
3 points by gkswamy98 25 days ago | 0 comments
Domain-Aware Fine-Tuning of Foundation Models (arxiv.org)
Machine Learning, Foundation Models, Fine-Tuning
12 points by PaulHoule 253 days ago | 0 comments
Fine-Tune Embeddings in Google Colab (research.google.com)
Fine-Tuning, Embeddings, Machine Learning, Google Colab
8 points by esleightholm 254 days ago | 1 comments
CURLoRA: Stable LLM Fine-Tuning and Catastrophic Forgetting Mitigation (zenodo.org)
Machine Learning, Fine-Tuning, Catastrophic Forgetting
62 points by mnoorfawi 263 days ago | 9 comments