dm.cs.tu-dortmund.de/mlbits/neural-nlp-finetuning/
Finetuning and Optimization – Lecture Notes
Dettmers, T., Pagnoni, A., Holtzman, A. and Zettlemoyer, L. 2023. QLoRA: Efficient finetuning of quantized LLMs. CoRR . abs/2305.14314, (2023). DOI: 10.48550/ARXIV.2305.14314
[FAHA22]
Frantar, E., Ashkboos [...] E., Ermon, S., Manning, C.D. and Finn, C. 2023. Direct preference optimization: Your language model is secretly a reward model. CoRR . abs/2305.18290, (2023). DOI: 10.48550/ARXIV.2305.18290
continue to [...] been optimally reformatted for online access. All rights reserved unless otherwise noted.
Finetuning
2023 was the year of open-source models: LLaMA, LLaMA 2, Mistral, …
open source optimization of models …
