%0 Conference Paper %1 conf/emnlp/HavrillaZPTTBAC23 %A Havrilla, Alexander %A Zhuravinskyi, Maksym %A Phung, Duy %A Tiwari, Aman %A Tow, Jonathan %A Biderman, Stella %A Anthony, Quentin %A Castricato, Louis %B EMNLP %D 2023 %E Bouamor, Houda %E Pino, Juan %E Bali, Kalika %I Association for Computational Linguistics %K dblp %P 8578-8595 %T trlX: A Framework for Large Scale Reinforcement Learning from Human Feedback. %U http://dblp.uni-trier.de/db/conf/emnlp/emnlp2023.html#HavrillaZPTTBAC23 %@ 979-8-89176-060-8

@inproceedings{conf/emnlp/HavrillaZPTTBAC23, added-at = {2024-04-12T00:00:00.000+0200}, author = {Havrilla, Alexander and Zhuravinskyi, Maksym and Phung, Duy and Tiwari, Aman and Tow, Jonathan and Biderman, Stella and Anthony, Quentin and Castricato, Louis}, biburl = {https://www.bibsonomy.org/bibtex/2ba0f373850d93f3478025be50e5c9ab9/dblp}, booktitle = {EMNLP}, crossref = {conf/emnlp/2023}, editor = {Bouamor, Houda and Pino, Juan and Bali, Kalika}, ee = {https://aclanthology.org/2023.emnlp-main.530}, interhash = {a252d90ee5a6426eb2b32ddf51093eec}, intrahash = {ba0f373850d93f3478025be50e5c9ab9}, isbn = {979-8-89176-060-8}, keywords = {dblp}, pages = {8578-8595}, publisher = {Association for Computational Linguistics}, timestamp = {2024-04-15T07:07:10.000+0200}, title = {trlX: A Framework for Large Scale Reinforcement Learning from Human Feedback.}, url = {http://dblp.uni-trier.de/db/conf/emnlp/emnlp2023.html#HavrillaZPTTBAC23}, year = 2023 }