Commits

Commits on Mar 5, 2024

add notebook
Jake-Song
committedMar 5, 2024

Commits on Mar 4, 2024

add notebook
Jake-Song
committedMar 4, 2024
add notebook
Jake-Song
committedMar 4, 2024

Commits on Feb 27, 2024

bigram2
Jake-Song
committedFeb 27, 2024
bigram: add notebook
Jake-Song
committedFeb 27, 2024

Commits on Feb 26, 2024

bigram: add notebook
Jake-Song
committedFeb 26, 2024
bigram: add notebook
Jake-Song
committedFeb 26, 2024

Commits on Nov 20, 2022

tune description of the repo wrt references
karpathy
committedNov 20, 2022

Commits on Sep 15, 2022

Merge pull request karpathy#3 from normanyu/fix-rnn-prev-state
karpathy
committedSep 15, 2022
Fix bug in RNN where hprev always referred to start. Change so that hprev refers to output of previous cell

Norman Yu
authored and
Norman Yu
committedSep 15, 2022

Commits on Sep 2, 2022

change readme
karpathy
committedSep 2, 2022

Commits on Aug 22, 2022

add a bag of words model that looks suspiciously similar to a transformer ;)
karpathy
committedAug 22, 2022
add an RNN and a GRU language model
karpathy
committedAug 22, 2022
generalize makemore into other types of language models, and add bigram LM and an MLP LM
karpathy
committedAug 22, 2022

Commits on Aug 20, 2022

fix comment
karpathy
committedAug 20, 2022
implementation of InfiniteDataLoader sad
karpathy
committedAug 20, 2022
remove some guardrails for this simple of a use case
karpathy
committedAug 20, 2022
remove gradient clipping i dont think its needed at this small scale
karpathy
committedAug 20, 2022
simplify optimizer init and delete code
karpathy
committedAug 20, 2022
remove weight init, not needed at this scale
karpathy
committedAug 20, 2022
add max steps
karpathy
committedAug 20, 2022

Commits on Aug 19, 2022

respect multigpu envs, e.g. cuda:2 designation should work
karpathy
committedAug 19, 2022
big refactor to make easier and api agree with mingpt more
karpathy
committedAug 19, 2022

Commits on Jun 9, 2022