Sandy4321

you mentioned here https://www.youtube.com/watch?v=Ic1oE6SEOBs Speed Up Your Code With Cython you have video about how to use cashing (cpu cash memory ) to speed up calculations what video is it...

do you know code example to run fully locally , without spark? kind of online learning?

6

do you know code example to run fully locally , without spark? kind of online learning?

can you share code for Graph Neural Networks

data downloading is not working for canada may you share link for another download service example for gmail drive ?

L1 regularization for LogisticRegression?

1

regarding to regularization for LogisticRegression https://nbviewer.jupyter.org/github/qinhanmin2014/tiny-sklearn/blob/master/linear_model/LogisticRegression.ipynb do you have L1 regularization as written in your reference http://fa.bianp.net/blog/2013/numerical-optimizers-for-logistic-regression/ Mathieu • 7 years ago Interesting post! I would mention more clearly that...

may you share full example for PinballLoss with data for multivariate regression for example data like https://github.com/strongio/quantile-regression-tensorflow/blob/master/mcycle https://github.com/strongio/quantile-regression-tensorflow/blob/master/Quantile%20Loss.ipynb per https://github.com/nhatsmrt/nn-toolbox/blob/86bbb8a88f1a873ff7a9f9cd0727c3e514335f66/tests/test_pinball.py class TestPinball: def test_pinball(self): """ Adopt from https://www.tensorflow.org/addons/api_docs/python/tfa/losses/PinballLoss """ target...

can you share paper https://dl.acm.org/doi/10.1145/3106426.3106484

is it better to change return x @ wte.T # [n_seq, n_embd] -> [n_seq, n_vocab] by x[-1] @ wte.T ? then we can use next_id = np.argmax(logits)

do you have video to this code in addition to your blog https://jaykmody.com/blog/gpt-from-scratch/

can it be run on windows ? meaning do I need on windows this line tensorflow-macos==2.11.0; sys_platform == 'darwin' and platform_machine == 'arm64' in https://github.com/jaymody/picoGPT/blob/main/requirements.txt