Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Ferret, Johan"'
Autor:
Cideron, Geoffrey, Agostinelli, Andrea, Ferret, Johan, Girgin, Sertan, Elie, Romuald, Bachem, Olivier, Perrin, Sarah, Ramé, Alexandre
Generative models are transforming creative domains such as music generation, with inference-time strategies like Classifier-Free Guidance (CFG) playing a crucial role. However, CFG doubles inference cost while limiting originality and diversity acro
Externí odkaz:
http://arxiv.org/abs/2410.06084
Autor:
Pignatelli, Eduardo, Ferret, Johan, Rockäschel, Tim, Grefenstette, Edward, Paglieri, Davide, Coward, Samuel, Toni, Laura
The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback is delayed
Externí odkaz:
http://arxiv.org/abs/2409.12798
Autor:
Gemma Team, Riviere, Morgane, Pathak, Shreya, Sessa, Pier Giuseppe, Hardin, Cassidy, Bhupatiraju, Surya, Hussenot, Léonard, Mesnard, Thomas, Shahriari, Bobak, Ramé, Alexandre, Ferret, Johan, Liu, Peter, Tafti, Pouya, Friesen, Abe, Casbon, Michelle, Ramos, Sabela, Kumar, Ravin, Lan, Charline Le, Jerome, Sammy, Tsitsulin, Anton, Vieillard, Nino, Stanczyk, Piotr, Girgin, Sertan, Momchev, Nikola, Hoffman, Matt, Thakoor, Shantanu, Grill, Jean-Bastien, Neyshabur, Behnam, Bachem, Olivier, Walton, Alanna, Severyn, Aliaksei, Parrish, Alicia, Ahmad, Aliya, Hutchison, Allen, Abdagic, Alvin, Carl, Amanda, Shen, Amy, Brock, Andy, Coenen, Andy, Laforge, Anthony, Paterson, Antonia, Bastian, Ben, Piot, Bilal, Wu, Bo, Royal, Brandon, Chen, Charlie, Kumar, Chintu, Perry, Chris, Welty, Chris, Choquette-Choo, Christopher A., Sinopalnikov, Danila, Weinberger, David, Vijaykumar, Dimple, Rogozińska, Dominika, Herbison, Dustin, Bandy, Elisa, Wang, Emma, Noland, Eric, Moreira, Erica, Senter, Evan, Eltyshev, Evgenii, Visin, Francesco, Rasskin, Gabriel, Wei, Gary, Cameron, Glenn, Martins, Gus, Hashemi, Hadi, Klimczak-Plucińska, Hanna, Batra, Harleen, Dhand, Harsh, Nardini, Ivan, Mein, Jacinda, Zhou, Jack, Svensson, James, Stanway, Jeff, Chan, Jetha, Zhou, Jin Peng, Carrasqueira, Joana, Iljazi, Joana, Becker, Jocelyn, Fernandez, Joe, van Amersfoort, Joost, Gordon, Josh, Lipschultz, Josh, Newlan, Josh, Ji, Ju-yeong, Mohamed, Kareem, Badola, Kartikeya, Black, Kat, Millican, Katie, McDonell, Keelin, Nguyen, Kelvin, Sodhia, Kiranbir, Greene, Kish, Sjoesund, Lars Lowe, Usui, Lauren, Sifre, Laurent, Heuermann, Lena, Lago, Leticia, McNealus, Lilly, Soares, Livio Baldini, Kilpatrick, Logan, Dixon, Lucas, Martins, Luciano, Reid, Machel, Singh, Manvinder, Iverson, Mark, Görner, Martin, Velloso, Mat, Wirth, Mateo, Davidow, Matt, Miller, Matt, Rahtz, Matthew, Watson, Matthew, Risdal, Meg, Kazemi, Mehran, Moynihan, Michael, Zhang, Ming, Kahng, Minsuk, Park, Minwoo, Rahman, Mofi, Khatwani, Mohit, Dao, Natalie, Bardoliwalla, Nenshad, Devanathan, Nesh, Dumai, Neta, Chauhan, Nilay, Wahltinez, Oscar, Botarda, Pankil, Barnes, Parker, Barham, Paul, Michel, Paul, Jin, Pengchong, Georgiev, Petko, Culliton, Phil, Kuppala, Pradeep, Comanescu, Ramona, Merhej, Ramona, Jana, Reena, Rokni, Reza Ardeshir, Agarwal, Rishabh, Mullins, Ryan, Saadat, Samaneh, Carthy, Sara Mc, Cogan, Sarah, Perrin, Sarah, Arnold, Sébastien M. R., Krause, Sebastian, Dai, Shengyang, Garg, Shruti, Sheth, Shruti, Ronstrom, Sue, Chan, Susan, Jordan, Timothy, Yu, Ting, Eccles, Tom, Hennigan, Tom, Kocisky, Tomas, Doshi, Tulsee, Jain, Vihan, Yadav, Vikas, Meshram, Vilobh, Dharmadhikari, Vishal, Barkley, Warren, Wei, Wei, Ye, Wenming, Han, Woohyun, Kwon, Woosuk, Xu, Xiang, Shen, Zhe, Gong, Zhitao, Wei, Zichuan, Cotruta, Victor, Kirk, Phoebe, Rao, Anand, Giang, Minh, Peran, Ludovic, Warkentin, Tris, Collins, Eli, Barral, Joelle, Ghahramani, Zoubin, Hadsell, Raia, Sculley, D., Banks, Jeanine, Dragan, Anca, Petrov, Slav, Vinyals, Oriol, Dean, Jeff, Hassabis, Demis, Kavukcuoglu, Koray, Farabet, Clement, Buchatskaya, Elena, Borgeaud, Sebastian, Fiedel, Noah, Joulin, Armand, Kenealy, Kathleen, Dadashi, Robert, Andreev, Alek
In this work, we introduce Gemma 2, a new addition to the Gemma family of lightweight, state-of-the-art open models, ranging in scale from 2 billion to 27 billion parameters. In this new version, we apply several known technical modifications to the
Externí odkaz:
http://arxiv.org/abs/2408.00118
Autor:
Wang, Kaiwen, Kidambi, Rahul, Sullivan, Ryan, Agarwal, Alekh, Dann, Christoph, Michi, Andrea, Gelmi, Marco, Li, Yunxuan, Gupta, Raghav, Dubey, Avinava, Ramé, Alexandre, Ferret, Johan, Cideron, Geoffrey, Hou, Le, Yu, Hongkun, Ahmed, Amr, Mehta, Aranyak, Hussenot, Léonard, Bachem, Olivier, Leurent, Edouard
Reward-based finetuning is crucial for aligning language policies with intended behaviors (e.g., creativity and safety). A key challenge is to develop steerable language models that trade-off multiple (conflicting) objectives in a flexible and effici
Externí odkaz:
http://arxiv.org/abs/2407.15762
Autor:
Sessa, Pier Giuseppe, Dadashi, Robert, Hussenot, Léonard, Ferret, Johan, Vieillard, Nino, Ramé, Alexandre, Shariari, Bobak, Perrin, Sarah, Friesen, Abe, Cideron, Geoffrey, Girgin, Sertan, Stanczyk, Piotr, Michi, Andrea, Sinopalnikov, Danila, Ramos, Sabela, Héliou, Amélie, Severyn, Aliaksei, Hoffman, Matt, Momchev, Nikola, Bachem, Olivier
Reinforcement learning from human feedback (RLHF) is a key driver of quality and safety in state-of-the-art large language models. Yet, a surprisingly simple and strong inference-time strategy is Best-of-N sampling that selects the best generation am
Externí odkaz:
http://arxiv.org/abs/2407.14622
Autor:
Ramé, Alexandre, Ferret, Johan, Vieillard, Nino, Dadashi, Robert, Hussenot, Léonard, Cedoz, Pierre-Louis, Sessa, Pier Giuseppe, Girgin, Sertan, Douillard, Arthur, Bachem, Olivier
Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human preferences. To prevent the forgetting of pre-trained knowledge, RLHF u
Externí odkaz:
http://arxiv.org/abs/2406.16768
Autor:
Botev, Aleksandar, De, Soham, Smith, Samuel L, Fernando, Anushan, Muraru, George-Cristian, Haroun, Ruba, Berrada, Leonard, Pascanu, Razvan, Sessa, Pier Giuseppe, Dadashi, Robert, Hussenot, Léonard, Ferret, Johan, Girgin, Sertan, Bachem, Olivier, Andreev, Alek, Kenealy, Kathleen, Mesnard, Thomas, Hardin, Cassidy, Bhupatiraju, Surya, Pathak, Shreya, Sifre, Laurent, Rivière, Morgane, Kale, Mihir Sanjay, Love, Juliette, Tafti, Pouya, Joulin, Armand, Fiedel, Noah, Senter, Evan, Chen, Yutian, Srinivasan, Srivatsan, Desjardins, Guillaume, Budden, David, Doucet, Arnaud, Vikram, Sharad, Paszke, Adam, Gale, Trevor, Borgeaud, Sebastian, Chen, Charlie, Brock, Andy, Paterson, Antonia, Brennan, Jenny, Risdal, Meg, Gundluru, Raj, Devanathan, Nesh, Mooney, Paul, Chauhan, Nilay, Culliton, Phil, Martins, Luiz Gustavo, Bandy, Elisa, Huntsperger, David, Cameron, Glenn, Zucker, Arthur, Warkentin, Tris, Peran, Ludovic, Giang, Minh, Ghahramani, Zoubin, Farabet, Clément, Kavukcuoglu, Koray, Hassabis, Demis, Hadsell, Raia, Teh, Yee Whye, de Frietas, Nando
We introduce RecurrentGemma, a family of open language models which uses Google's novel Griffin architecture. Griffin combines linear recurrences with local attention to achieve excellent performance on language. It has a fixed-sized state, which red
Externí odkaz:
http://arxiv.org/abs/2404.07839
Autor:
Gemma Team, Mesnard, Thomas, Hardin, Cassidy, Dadashi, Robert, Bhupatiraju, Surya, Pathak, Shreya, Sifre, Laurent, Rivière, Morgane, Kale, Mihir Sanjay, Love, Juliette, Tafti, Pouya, Hussenot, Léonard, Sessa, Pier Giuseppe, Chowdhery, Aakanksha, Roberts, Adam, Barua, Aditya, Botev, Alex, Castro-Ros, Alex, Slone, Ambrose, Héliou, Amélie, Tacchetti, Andrea, Bulanova, Anna, Paterson, Antonia, Tsai, Beth, Shahriari, Bobak, Lan, Charline Le, Choquette-Choo, Christopher A., Crepy, Clément, Cer, Daniel, Ippolito, Daphne, Reid, David, Buchatskaya, Elena, Ni, Eric, Noland, Eric, Yan, Geng, Tucker, George, Muraru, George-Christian, Rozhdestvenskiy, Grigory, Michalewski, Henryk, Tenney, Ian, Grishchenko, Ivan, Austin, Jacob, Keeling, James, Labanowski, Jane, Lespiau, Jean-Baptiste, Stanway, Jeff, Brennan, Jenny, Chen, Jeremy, Ferret, Johan, Chiu, Justin, Mao-Jones, Justin, Lee, Katherine, Yu, Kathy, Millican, Katie, Sjoesund, Lars Lowe, Lee, Lisa, Dixon, Lucas, Reid, Machel, Mikuła, Maciej, Wirth, Mateo, Sharman, Michael, Chinaev, Nikolai, Thain, Nithum, Bachem, Olivier, Chang, Oscar, Wahltinez, Oscar, Bailey, Paige, Michel, Paul, Yotov, Petko, Chaabouni, Rahma, Comanescu, Ramona, Jana, Reena, Anil, Rohan, McIlroy, Ross, Liu, Ruibo, Mullins, Ryan, Smith, Samuel L, Borgeaud, Sebastian, Girgin, Sertan, Douglas, Sholto, Pandya, Shree, Shakeri, Siamak, De, Soham, Klimenko, Ted, Hennigan, Tom, Feinberg, Vlad, Stokowiec, Wojciech, Chen, Yu-hui, Ahmed, Zafarali, Gong, Zhitao, Warkentin, Tris, Peran, Ludovic, Giang, Minh, Farabet, Clément, Vinyals, Oriol, Dean, Jeff, Kavukcuoglu, Koray, Hassabis, Demis, Ghahramani, Zoubin, Eck, Douglas, Barral, Joelle, Pereira, Fernando, Collins, Eli, Joulin, Armand, Fiedel, Noah, Senter, Evan, Andreev, Alek, Kenealy, Kathleen
This work introduces Gemma, a family of lightweight, state-of-the art open models built from the research and technology used to create Gemini models. Gemma models demonstrate strong performance across academic benchmarks for language understanding,
Externí odkaz:
http://arxiv.org/abs/2403.08295
Autor:
Guo, Shangmin, Zhang, Biao, Liu, Tianlin, Liu, Tianqi, Khalman, Misha, Llinares, Felipe, Rame, Alexandre, Mesnard, Thomas, Zhao, Yao, Piot, Bilal, Ferret, Johan, Blondel, Mathieu
Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF), that do not require a separate reward model. However, the preference datasets used in
Externí odkaz:
http://arxiv.org/abs/2402.04792
Autor:
Ramé, Alexandre, Vieillard, Nino, Hussenot, Léonard, Dadashi, Robert, Cideron, Geoffrey, Bachem, Olivier, Ferret, Johan
Aligning large language models (LLMs) with human preferences through reinforcement learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward model (RM) to achieve seemingly high rewards without meeting the underlying objec
Externí odkaz:
http://arxiv.org/abs/2401.12187