Methods › General › Fine-Tuning
Fine-Tuning
The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 7 of the 9 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.
Text 1, carried by 6 of 9 methods:
Fine-Tuning methods in deep learning take existing trained networks and 'fine-tune' them to a new task so that information contained in the weights can be repurposed. Below you can find a continuously updating list of fine-tuning methods.
Text 2, carried by 1 of 9 methods:
Language Models are models for predicting the next word or character in a document. Below you can find a continuously updating list of language models.
Methods
All 9 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| Discriminative Fine-Tuning | – | 1,990 |
| Virtual Data Augmentation | – | 4 |
| Leverage Learning | – | 3 |
| Child-Tuning | – | 1 |
| DSiRe Dataset Size Recovery | – | 1 |
| ERNIE-GEN | – | 1 |
| MixLoRA | – | 1 |
| SORSA Singular Values and Orthonormal Regularized Singular Vectors Adaptation | – | 1 |
| Spectral DeTuning | – | 1 |