Urmăriți
Jacob Portes
Jacob Portes
MosaicML x Databricks
Adresă de e-mail confirmată pe databricks.com - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Resting-state hemodynamics are spatiotemporally coupled to synchronized and symmetric neural activity in excitatory neurons
Y Ma, MA Shaik, MG Kozberg, SH Kim, JP Portes, D Timerman, ...
Proceedings of the National Academy of Sciences 113 (52), E8463-E8471, 2016
3592016
Introducing mpt-7b: A new standard for open-source, commercially usable llms
MosaicML NLP Team
DataBricks (May, 2023) www. mosaicml. com/blog/mpt-7b, 2023
289*2023
Lora learns less and forgets less
D Biderman, J Portes, JJG Ortiz, M Paul, P Greengard, C Jennings, ...
Transactions on Machine Learning Research, 2024
1082024
Introducing mpt-30b: Raising the bar for open-source foundation models
MosaicML NLP Team
Accessed, 2023
512023
Beyond chinchilla-optimal: Accounting for inference in language model scaling laws
N Sardana, J Frankle
arXiv preprint arXiv:2401.00448, 2023
442023
Flexible filtering by neural inputs supports motion computation across states and stimuli
JR Kohn, JP Portes, MP Christenson, LF Abbott, R Behnia
Current biology 31 (23), 5249-5260. e5, 2021
282021
Introducing DBRX: a new state-of-the-art open LLM
Mosaic Research Team
Mosaic AI Research, 2024
24*2024
MosaicBERT: A bidirectional encoder optimized for fast pretraining
J Portes, A Trott, S Havens, D King, A Venigalla, M Nadeem, N Sardana, ...
Advances in Neural Information Processing Systems 36, 3106-3130, 2023
22*2023
Limit: Less is more for instruction tuning across evaluation paradigms
A Jha, S Havens, J Dohmann, A Trott, J Portes
arXiv preprint arXiv:2311.13133, 2023
112023
Distinguishing learning rules with brain machine interfaces
J Portes, C Schmid, JM Murray
Advances in neural information processing systems 35, 25937-25950, 2022
112022
Long context rag performance of large language models
Q Leng, J Portes, S Havens, M Zaharia, M Carbin
arXiv preprint arXiv:2411.03538, 2024
72024
Fast benchmarking of accuracy vs. training time with cyclic learning rates
J Portes, D Blalock, C Stephenson, J Frankle
arXiv preprint arXiv:2206.00832, 2022
42022
State and stimulus dependence reconcile motion computation and the Drosophila connectome
JR Kohn, JP Portes, MP Christenson, LF Abbott, R Behnia
bioRxiv, 2021.04. 17.440267, 2021
32021
Flexible Computation in Neural Circuits
JP Portes
Columbia University, 2022
2022
DECOHERENCE, SUPERCONDUCTING QUBITS, AND THE POSSIBILITY OF QUANTUM COMPUTING-DRAFT
J Portes
2015
Logical Idealism & Einstein’s Theory of Relativity
J Portes
2015
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–16