%0 Generic %1 touvron2023llama %A Touvron, Hugo %A Lavril, Thibaut %A Izacard, Gautier %A Martinet, Xavier %A Lachaux, Marie-Anne %A Lacroix, Timothée %A Rozière, Baptiste %A Goyal, Naman %A Hambro, Eric %A Azhar, Faisal %A Rodriguez, Aurelien %A Joulin, Armand %A Grave, Edouard %A Lample, Guillaume %D 2023 %K facebook llm meta model pretrained %T LLaMA: Open and Efficient Foundation Language Models %U http://arxiv.org/abs/2302.13971 %X We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.

@misc{touvron2023llama, abstract = {We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, without resorting to proprietary and inaccessible datasets. In particular, LLaMA-13B outperforms GPT-3 (175B) on most benchmarks, and LLaMA-65B is competitive with the best models, Chinchilla-70B and PaLM-540B. We release all our models to the research community.}, added-at = {2023-03-29T15:33:41.000+0200}, author = {Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timothée and Rozière, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume}, biburl = {https://www.bibsonomy.org/bibtex/2731b422f753eccd5c5d65fbde4856c6d/jil}, description = {[2302.13971] LLaMA: Open and Efficient Foundation Language Models}, interhash = {03a85d2a0612b9704acf6884edbe60aa}, intrahash = {731b422f753eccd5c5d65fbde4856c6d}, keywords = {facebook llm meta model pretrained}, note = {cite arxiv:2302.13971}, timestamp = {2023-03-29T15:34:56.000+0200}, title = {LLaMA: Open and Efficient Foundation Language Models}, url = {http://arxiv.org/abs/2302.13971}, year = 2023 }