Hi Teams,
Congratulate on this impressive model! I have a question about the language model packing strategy discussed in the paper. Currently, I am also trying something similar to https://arxiv.org/abs/2310.10638, but no luck yet. Could you please share more details and insights about this method? Thanks!
Hi Teams, Congratulate on this impressive model! I have a question about the language model packing strategy discussed in the paper. Currently, I am also trying something similar to https://arxiv.org/abs/2310.10638, but no luck yet. Could you please share more details and insights about this method? Thanks!