Coding a ChatGPT Like Transformer from Scratch in PyTorch

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: G. Dall’Olio, D. Negrusa, S. Cogorno, D. Dickie, S. Ágoston, M. Steenbergen, P. Keener, S. Kundapurkar, JWC, BufferUnderrrun, J. Le, D. Greene, D. Schioberg, Z. Rosenberg, H-M Chang, R. Summe, Y. El Hamzaoui, G. Cia, R. Zhang, M. Ayoubieh, Losings, F. Pedemonte, S. Song US, L. Cisterna, J. Alexander

The Matrix Math Behind Transformer Neural Networks

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: G. Dall’Olio, D. Negrusa, S. Cogorno, D. Dickie, S. Ágoston, P. Keener, S. Kundapurkar, JWC, BufferUnderrrun, J. Le, D. Greene, D. Schioberg, Z. Rosenberg, H-M Chang, R. Summe, Y. El Hamzaoui, H. Probe, G. Cia, R. Zhang, M. Ayoubieh, Losings, F. Pedemonte, S. Song US, A. Tolkachev, L. Cisterna, J. Alexander

Essential Matrix Algebra for Neural Networks, Clearly Explained!!!

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: D. Negrusa, S. Cogorno, D. Dickie, S. Ágoston, M. Steenbergen, P. Keener, Alex, S. Kundapurkar, JWC, BufferUnderrrun, S. Handschuh, J. Le, D. Greene, D. Schioberg, Z. Rosenberg, H-M Chang, R. Zhang, M. Ayoubieh, Losings, F. Pedemonte, S. Song US, A. Tolkachev, L. Cisterna, J. Alexander

Word Embedding in PyTorch + Lightning

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: S. Cogorno, D. Dickie, S. Ágoston, M. Steenbergen, P. Keener, Alex, S. Kundapurkar, JWC, BufferUnderrrun, S. Handschuh, J. Le, D. Greene, D. Schioberg, Z. Rosenberg, H-M Chang, R. Zhang, M. Ayoubieh, Losings, F. Pedemonte, S. Song US, A. Tolkachev, L. Cisterna, J. Alexander

Attention for Neural Networks

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: S. Ágoston, M. Steenbergen, P. Keener, A. Rabatin, Alex, S. Kundapurkar, JWC, S. Jeffcoat, S. Handschuh, J. Le, D. Greene, D. Schioberg, Magpie, Z. Rosenberg, J. N., H-M Chang, M. Ayoubieh, S. Kundapurkar, Losings, F. Pedemonte, S. Song US, A. Tolkachev, L. Cisterna, J. Alexander

Sequence-to-Sequence (seq2seq) Encoder-Decoder Neural Networks, Clearly Explained!!!

NOTE: This StatQuest was supported by these awesome people who support StatQuest at the Double BAM level: P. Keener, A. Rabatin, Alex, S. Kundapurkar, JWC, BufferUnderrun, S. Jeffcoat, S. Handschuh, J. Le, D. Greene, D. Schioberg, Magpie, Z. Rosenberg, J. N., H-M Chang, M. Ayoubieh, Y. Liu, S. Kundapurkar, Losings, F. Pedemonte, S. Song US, A. Tolkachev, L. Cisterna, J. Alexander