Commit Graph

  • 8c1f1b280f Update README.md: format notable forks madroid 2023-08-06 14:23:57 +08:00
  • 49e3ff6d08 update makefile to use correct arg call after our argparse update Andrej Karpathy 2023-08-05 23:11:11 +00:00
  • a1037d79ee turned on trimTrailingWhitespace in my vscode sorry about that Andrej Karpathy 2023-08-05 22:46:35 +00:00
  • a2962b9a0c Merge pull request #195 from clebert/prompt-tokens-size Andrej 2023-08-05 15:29:33 -07:00
  • bdf3a6c22c Merge pull request #167 from mzcu/pretokenize-speedup Andrej 2023-08-05 15:14:51 -07:00
  • d1a59a9ca8 use EXIT_FAILURE instead of 1 Andrej Karpathy 2023-08-05 19:19:49 +00:00
  • f3e7710763 Merge pull request #215 from Majdoddin/windows Andrej 2023-08-05 12:14:39 -07:00
  • 0447b06e7c simplify rope Andrej Karpathy 2023-08-05 18:41:31 +00:00
  • 8719d5f5a8 Merge branch 'mpcusack-mpcusack/jitsave' Andrej Karpathy 2023-08-05 18:13:07 +00:00
  • e03d7ecf12 Merge branch 'mpcusack/jitsave' of https://github.com/mpcusack/llama2.c into mpcusack-mpcusack/jitsave Andrej Karpathy 2023-08-05 18:11:21 +00:00
  • 0609eb6601 slightly tune todos Andrej Karpathy 2023-08-05 17:13:35 +00:00
  • dcef5ff7c7 add a bit less embarassing argparse that uses keyword arguments instead of positional arguments Andrej Karpathy 2023-08-05 17:08:11 +00:00
  • 837796e0b7 get rid of unneeded comment now Andrej Karpathy 2023-08-05 16:19:27 +00:00
  • db4ad580f3 Merge pull request #225 from RahulSChand/rope_changes Andrej 2023-08-05 09:18:47 -07:00
  • 9d001c6249 Merge pull request #223 from LexiestLeszek/master-1 Andrej 2023-08-05 09:13:12 -07:00
  • f93e7b5626 Merge pull request #228 from aiwizzard/master Andrej 2023-08-05 09:09:19 -07:00
  • 2abd77a57f Merge pull request #231 from madroidmaq/master Andrej 2023-08-05 09:08:59 -07:00
  • ba036696b7 Merge branch 'master' into master Andrej 2023-08-05 09:08:51 -07:00
  • 4b1e5d57a1 Merge pull request #232 from clebert/zig-port Andrej 2023-08-05 09:08:31 -07:00
  • 13f342af9e docs typo Michael Cusack 2023-08-04 23:12:06 +07:00
  • f4c96b7339 Add options to save_torchscript Michael Cusack 2023-08-04 23:11:33 +07:00
  • 4b3a41b8fc Add options to save_torchscript Michael Cusack 2023-08-04 23:10:14 +07:00
  • a4e961f378 Add Zig port to README Clemens Akens 2023-08-04 18:00:04 +02:00
  • 113c675bc9 Rename save_model.py Michael Cusack 2023-08-04 20:31:44 +07:00
  • ec65aac182 Update README.md: add a Kotlin port of this project madroid 2023-08-04 18:50:06 +08:00
  • 305d920862 Zero'ing params docs Michael Cusack 2023-08-04 17:33:23 +07:00
  • dfff7812db Zero'ing params docs Michael Cusack 2023-08-04 17:31:31 +07:00
  • 34f0402501 Zero'ing params docs Michael Cusack 2023-08-04 17:31:11 +07:00
  • d4cdd6259e Zero'ing params docs Michael Cusack 2023-08-04 17:30:05 +07:00
  • 9f8e0857ee Typo Michael Cusack 2023-08-04 17:22:27 +07:00
  • f8d45f180d Reinline loss function Michael Cusack 2023-08-04 17:21:29 +07:00
  • f67185958b Model args in save script Michael Cusack 2023-08-04 17:07:41 +07:00
  • fd5e2cc7bc Updating training code for loss result Michael Cusack 2023-08-04 17:03:11 +07:00
  • ac2b435151 docs Michael Cusack 2023-08-04 16:55:26 +07:00
  • 11a8348dfc extra line Michael Cusack 2023-08-04 16:52:04 +07:00
  • f2e34e6b0a Resolve jit.save errors Michael Cusack 2023-08-04 16:49:26 +07:00
  • b9f303f3b8 Fixed typo in README.md Ajmal K 2023-08-04 10:30:11 +05:30
  • 02cf3c7311 Small changes to ROPE & comments rahulschand 2023-08-03 20:13:50 +05:30
  • 99ea2f7070 Updated README.md with added steps for junior devs Leszek Mielnikow 2023-08-03 09:10:13 +02:00
  • af8708d87b Merge pull request #216 from gohai/patch-1 Andrej 2023-08-02 10:06:09 -07:00
  • 9819ae4b3d Merge branch 'master' into patch-1 Andrej 2023-08-02 10:06:01 -07:00
  • 5b47cd1cfb Merge pull request #211 from wlamond/tinyshakespeare Andrej 2023-08-02 09:42:11 -07:00
  • 574be29e4f Merge pull request #217 from mukel/llama2.java Andrej 2023-08-02 09:40:02 -07:00
  • 30974307af Add Java port. Alfonso² Peterssen 2023-08-02 15:01:28 +02:00
  • 8dd9baddaa Update README.md Gottfried Haider 2023-08-02 18:09:06 +08:00
  • b2b5514a92 Add link to Emscripten port in README Gottfried Haider 2023-08-02 17:58:15 +08:00
  • f50804a5ae replaced __int64 with int64_t and DWORD with uint_32 Ruhollah Majdoddin 2023-08-02 10:18:30 +02:00
  • e592ed5d64 Add tinyshakespeare dataset Will Lamond 2023-07-30 06:14:38 -07:00
  • a8f3e1c499 Merge pull request #175 from tairov/ci-mingw Andrej 2023-08-01 09:02:35 -07:00
  • b7f026ffc8 Merge pull request #179 from richinseattle/windows-ftell64-fix Andrej 2023-08-01 09:01:50 -07:00
  • e2d4a386c7 Merge pull request #186 from vodkaslime/master Andrej 2023-08-01 09:00:37 -07:00
  • e270c6eb3c Update README.md: add mention of -f unroll loops option for gcc Andrej 2023-08-01 08:59:00 -07:00
  • 23f608350a Merge branch 'master' into master Andrej 2023-08-01 08:50:52 -07:00
  • def12a29c6 Merge pull request #173 from juvi21/patch-1 Andrej 2023-08-01 08:50:14 -07:00
  • 221f4f929f Merge branch 'master' into patch-1 Andrej 2023-08-01 08:50:08 -07:00
  • e06ff42bc3 Merge pull request #160 from GabrielJadderson/add-fp-fast Andrej 2023-08-01 08:49:43 -07:00
  • c1a0c6e63e Merge pull request #198 from trholding/notable-forks-patch Andrej 2023-08-01 08:49:18 -07:00
  • 217667d085 Merge branch 'master' into notable-forks-patch Andrej 2023-08-01 08:49:08 -07:00
  • 9023840fe0 Merge branch 'master' into master Andrej 2023-08-01 08:34:23 -07:00
  • 4a1250e874 Merge pull request #149 from murilocurti/fix/makefile-win64-gcc Andrej 2023-08-01 08:32:20 -07:00
  • 71e5de2136 Merge branch 'ai-doge-master' Andrej Karpathy 2023-08-01 15:27:00 +00:00
  • 502f6816d6 Merge branch 'master' of https://github.com/ai-doge/llama2.c into ai-doge-master Andrej Karpathy 2023-08-01 15:25:14 +00:00
  • f971b76008 Merge pull request #188 from leo-du/llama2.c Andrej 2023-08-01 08:21:06 -07:00
  • 9942a33ae2 Merge pull request #194 from celikin/patch-1 Andrej 2023-08-01 08:20:50 -07:00
  • 13d22efe48 Merge branch 'master' into llama2.c Andrej 2023-08-01 08:19:31 -07:00
  • 163e2648c4 Merge pull request #197 from jrudolph/add-scala-port Andrej 2023-08-01 08:07:30 -07:00
  • 338f606c59 Merge branch 'master' into patch-1 juvi 2023-08-01 12:36:19 +02:00
  • 883cda1a2c fix freq_cos, freq_sin serialize aidoge 2023-08-01 16:31:43 +08:00
  • 4c0a88249d add link to scala port Johannes Rudolph 2023-07-31 14:59:11 +02:00
  • d0702edf1f README.md - Update notable forks section Vulcan 2023-07-31 18:12:56 +05:30
  • 2c0134f669 adjust malloc size for prompt_tokens Clemens Akens 2023-07-31 14:11:15 +02:00
  • 3b446baeb3 update readme Leo Du 2023-07-31 03:34:34 -04:00
  • 68fc522139 add vodkaslime llama.zig to readme vodkaslime 2023-07-31 10:15:04 +08:00
  • ce05cc28cf Merge pull request #178 from cgbur/patch-1 Andrej 2023-07-30 18:15:24 -07:00
  • b63dfd596f clean up windows mmap, drop 32bit support richinseattle 2023-07-30 01:03:34 -07:00
  • 6b6ed3db97 update mmap.c to use ssize_t instead of off_t for 64bit richinseattle 2023-07-30 00:03:38 -07:00
  • 13789ffe2c Added julia port to notable forks section in README.md juvi 2023-07-30 09:00:27 +02:00
  • cddb05d5b2 use ssize_t/int64 and 64bit version of ftell on windows richinseattle 2023-07-29 22:46:38 -07:00
  • ab39930d27 Update README.md Chris Burgess 2023-07-30 01:53:48 -04:00
  • bc36686786 Add build step for win64 msys2/mingw Aydyn Tairov 2023-07-29 23:55:23 +01:00
  • 6f156fd5ac Added Julia port to notable forks section in README.md juvi 2023-07-29 16:56:40 +02:00
  • af3f3a7b31 Speed up tinystories pretokenize command Milos Cubrilo 2023-07-29 00:14:10 +02:00
  • f61807d6ea Merge pull request #163 from epicure/patch-1 Andrej 2023-07-28 11:13:28 -07:00
  • 43d19ed83c Update README.md seung joon choi 2023-07-29 02:44:46 +09:00
  • 356f74cc31 Add fp fast for better performance on windows Gabriel Jadderson 2023-07-28 17:21:31 +02:00
  • 3418fed02b added repository in readme Daniil Tcelikin 2023-07-28 14:53:00 +03:00
  • fd68dd222f reshuffle blocks of code a bit Andrej Karpathy 2023-07-28 05:37:43 +00:00
  • d04336cac8 Merge pull request #138 from aegkmq/better-rng Andrej 2023-07-27 22:33:14 -07:00
  • 6ce28fb388 Merge branch 'master' into better-rng aegkmq 2023-07-28 13:52:34 +09:00
  • 9949c50758 readme tweaks Andrej Karpathy 2023-07-28 04:43:33 +00:00
  • 2efc197c8f oops readme smallfix Andrej Karpathy 2023-07-28 04:36:53 +00:00
  • 905c5c58d0 add mention of prompting into readme Andrej Karpathy 2023-07-28 04:27:38 +00:00
  • 7cbb47cc36 update export_meta_llama_bin, get freqs_cos, freqs_sin independently. aidoge 2023-07-28 11:07:36 +08:00
  • b4bb47bb7b big change: adding prompting. many LOC, but critical. ty @atamurad for the first draft, i ended up tuning it quite a bit. Andrej Karpathy 2023-07-28 04:12:54 +00:00
  • 72ba34c392 fix: Use correct compiler for Win64 GCC in Makefile Murilo Curti 2023-07-27 21:39:09 -03:00
  • 568a651c45 slightly tune todos of the project Andrej Karpathy 2023-07-27 23:03:35 +00:00
  • e5752e1fc9 strip leading whitespace Andrej Karpathy 2023-07-27 22:59:19 +00:00
  • 25b50ee0e2 small stylistic fixes and adjustments, fix bug in Makefile, and change the timing code to skip the first (slow) iteration Andrej Karpathy 2023-07-27 22:42:08 +00:00
  • 0e1b0d4c93 Merge branch 'master' of github.com:karpathy/llama2.c Andrej Karpathy 2023-07-27 22:22:03 +00:00
  • 78952fb0b4 propagate the dropout flag Andrej Karpathy 2023-07-27 22:20:31 +00:00