glossary termAngestromTrust 60Published 2mo agoLive · 2mo ago
Fine-tuning
Further training a pretrained model on a smaller, specific dataset.
Further training a pretrained model on a smaller, specific dataset. Further training a pretrained model on a smaller, specific dataset.
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownFine-tune a small model on your own data →
- LinkedLinked via unknownInstead of decentralized training effort we should build the “One dataset” →
- LinkedLinked via unknownKnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models →
- PossiblePossibly related (embedding) · 46%gemseo/dev/gemseo-mlearning →
- PossiblePossibly related (embedding) · 52%data_ingenieur/s10-machine-learning-supervise →
- PossiblePossibly related (embedding) · 49%Hyperparameter tuning approach question [R] →
- PossiblePossibly related (embedding) · 55%UltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editing →
- PossiblePossibly related (embedding) · 46%Training an LLM from scratch on 1800's texts (160GB dataset) →
Related to
Covers (incoming)
Related to (incoming)
Related across the graph
tutorialFine-tune a small model on your own datarepodata_ingenieur/s10-machine-learning-supervisepaperKnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation ModelspaperUltraX: Refining Pre-Training Data at Scale with Adaptive Programmatic Editingrepogemseo/dev/gemseo-mlearningrepoinvergent-ai/surogaterepoYog-Sotho/LLM-fine-tunernewsI trained a 0.5M model on 1B tokens of Fineweb-edu dataset.newsThinking and rethinking data AI readinessnewsTraining an LLM from scratch on 1800's texts (160GB dataset)newsInstead of decentralized training effort we should build the “One dataset”newsHyperparameter tuning approach question [R]