Commit Graph

  • 25494f9cbc Have DDP ignore freqs_cis to avoid broadcast Andrew Gu 2023-07-24 13:58:09 +00:00
  • d95c7617c6 typo hu-po 2023-07-24 07:35:12 -05:00
  • 4d637983ad Fix tokenizer reading on Windows Henri Vasserman 2023-07-24 11:08:29 +03:00
  • 0a0ca73c65 [openmp] 1.5x inference speedup Kris Jusiak 2023-07-24 01:49:29 -05:00
  • d548245321 readme update; -Ofast enables the other ones so they become spurious Andrej Karpathy 2023-07-24 05:20:21 +00:00
  • 0e4076cd52 Merge pull request #25 from wsmoses/master Andrej 2023-07-23 22:12:28 -07:00
  • f6388c99c8 delete the copy function in favor of memcpy. sadly we have to import string.h now... Andrej Karpathy 2023-07-24 05:10:55 +00:00
  • 65e07462e4 Add information on compiler flags William Moses 2023-07-23 19:08:17 -10:00
  • b2204e1633 include example story from 44m model Andrej Karpathy 2023-07-24 04:57:30 +00:00
  • ba6acc9378 add pointer to the new 44M param model. which is still way too fast to inference, i have to train an even bigger one. Andrej Karpathy 2023-07-24 04:53:37 +00:00
  • 99354a85ce get rid of compiler warnings from ignoring return value of fread Andrej Karpathy 2023-07-24 04:39:24 +00:00
  • 6a61831e19 make init code much less sketchy Andrej Karpathy 2023-07-24 04:22:32 +00:00
  • bd9e837b14 Merge pull request #23 from awgu/pt2 Andrej 2023-07-23 21:08:17 -07:00
  • 3bfa5665d1 delete the run_wrap file! yay. ty @python273 and @ggerganov for code snippets Andrej Karpathy 2023-07-24 04:02:57 +00:00
  • af3b5c0364 Register freqs_cis as non-persistent buffer Andrew Gu 2023-07-24 03:09:03 +00:00
  • 44ecc784da performance guide tweak Andrej 2023-07-23 20:09:25 -07:00
  • f4e2cc7d96 Add performance optimization section Andrej 2023-07-23 20:04:39 -07:00
  • d7e2c46915 slight tweaks to softmax Andrej Karpathy 2023-07-24 02:02:12 +00:00
  • 7d6208870e Merge pull request #19 from mcognetta/master Andrej 2023-07-23 18:57:23 -07:00
  • 15e7c92fad Merge pull request #10 from luigifcruz/patch-1 Andrej 2023-07-23 18:52:36 -07:00
  • 80679e24be simplify softmax Marco Cognetta 2023-07-24 10:51:46 +09:00
  • 1b63a9510e Merge pull request #16 from zejunh/master Andrej 2023-07-23 18:38:12 -07:00
  • 1eb111adc7 Turn -funsafe-math-optimizations optional. Luigi Cruz 2023-07-23 20:09:45 -03:00
  • dc3962f356 remove unused parameter Junny 2023-07-23 15:33:29 -07:00
  • f9da392147 Add missing flag. Luigi Cruz 2023-07-23 17:14:11 -03:00
  • 114d8cfcb6 Add -funsafe-math-optimizations flag. Luigi Cruz 2023-07-23 17:08:27 -03:00
  • 7d401d530c Merge pull request #5 from danielgross/pleasantify-dx Andrej 2023-07-23 11:58:03 -07:00
  • 3b7b4878b4 compile with -O3 to increase tok/s from 18 to 98! wow, i have to train a bigger model now Andrej Karpathy 2023-07-23 18:55:46 +00:00
  • 8c383c28f9 Update README.md Daniel Gross 2023-07-23 10:46:36 -07:00
  • 518524f458 default to whatever system has Daniel Gross 2023-07-23 10:41:03 -07:00
  • fa872540ba fix comments in readme about spaces Andrej Karpathy 2023-07-23 17:11:35 +00:00
  • 5baaf9df06 small format tweaks, get rid of prints in tokenizer Andrej Karpathy 2023-07-23 17:09:23 +00:00
  • deb3818db9 Merge pull request #1 from sumo43/master Andrej 2023-07-23 10:07:40 -07:00
  • ad67d5e29c strike one tiny todo Andrej Karpathy 2023-07-23 17:05:22 +00:00
  • 353266aaae Merge pull request #3 from vovw/master Andrej 2023-07-23 10:04:42 -07:00
  • 13d7827ba4 added requirement.txt voidz7 2023-07-23 22:31:16 +05:30
  • 0bddcd94c1 Update run_wrap.py Artem Yatsenko 2023-07-23 09:28:49 -07:00
  • 00727ba1c0 Update README.md Andrej 2023-07-23 09:00:26 -07:00
  • 4af4b8abd4 add sample output story Andrej Karpathy 2023-07-23 15:59:19 +00:00
  • 523ba69578 fix readme Andrej Karpathy 2023-07-23 15:29:37 +00:00
  • 24917b23de fix run command Andrej Karpathy 2023-07-23 15:28:24 +00:00
  • 0c2a880063 add my pretrained model links Andrej Karpathy 2023-07-23 15:24:23 +00:00
  • 9414e7a45e tweaks and add a simple test Andrej Karpathy 2023-07-23 14:52:08 +00:00
  • f499d9d2b5 delete debug line Andrej Karpathy 2023-07-23 05:37:44 +00:00
  • 405eefded1 Update README.md Andrej 2023-07-22 22:35:38 -07:00
  • 9148cae17d Update README.md Andrej 2023-07-22 22:30:25 -07:00
  • 60d32cf13a move lines around Andrej Karpathy 2023-07-23 05:25:07 +00:00
  • 5b161abb9a somewhere ~20 hours later Andrej Karpathy 2023-07-23 05:23:45 +00:00
  • 731657856e Initial commit Andrej 2023-07-22 22:15:06 -07:00