schihei/llama2.c
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 517763346d HF checkpoints i removed the optimizer to save space, init Adam without the first/second moments is ok Andrej Karpathy 2023-07-27 22:20:07 +00:00
  • 747db60562 Merge pull request #133 from nikolaydubina/patch-1 Andrej 2023-07-27 15:08:21 -07:00
  • 6b3a689d96 Merge pull request #146 from admu-progvar/master Andrej 2023-07-27 15:07:58 -07:00
  • b63cb91303 Add llama2.cpp to notable forks section Franz Louis Cesista 2023-07-28 05:06:37 +08:00
  • 459b9c8561 Merge branch 'master' into patch-1 Nikolay Dubina 2023-07-28 01:19:10 +08:00
  • cc66a2037e Merge pull request #86 from tairov/master Andrej 2023-07-27 08:59:00 -07:00
  • b6d63a973e Merge branch 'tairov-win-timing' Andrej Karpathy 2023-07-27 15:43:58 +00:00
  • 677bb8fddd Merge branch 'win-timing' of https://github.com/tairov/llama2.c into tairov-win-timing Andrej Karpathy 2023-07-27 15:43:41 +00:00
  • b4b9ef5c6c add github actions workflow to validate builds on changes in *.c, *.h files Aydyn Tairov 2023-07-25 22:20:07 +01:00
  • 71200f3092 Fix random_f32 aegkmq 2023-07-28 00:35:59 +09:00
  • 9253d458f1 Merge pull request #139 from tairov/gnu Andrej 2023-07-27 08:35:57 -07:00
  • 343572675f minor whitespaces cleanup Aydyn Tairov 2023-07-27 16:30:22 +01:00
  • acf1e18e8f remove second ifdefs for windows timing by introducing ported version of clock_gettime Aydyn Tairov 2023-07-27 15:38:45 +01:00
  • 79933a8ab4 Merge pull request #137 from tatellos/master Andrej 2023-07-27 08:30:20 -07:00
  • 4a4663a235 Merge pull request #134 from Manuel030/sync-with-upstream Andrej 2023-07-27 08:28:30 -07:00
  • e970c275cf Update README.md Nikolay Dubina 2023-07-27 22:47:34 +08:00
  • 2566ddf744 add README section for centos 7 & amazon linux make target Aydyn Tairov 2023-07-27 15:00:27 +01:00
  • bddde3398a add Makefile option to support builds on amazon linux & centos Aydyn Tairov 2023-07-27 14:38:28 +01:00
  • 1bdf5af743 Replace the rand() with a portable PRNG aegkmq 2023-07-27 20:14:08 +09:00
  • abfcdf141e Improve readme: clarify dependencies and other things to install Mathias Arens 2023-07-27 13:05:32 +02:00
  • 9c0850daf7 add llama2.c-android to readme Manuel Plank 2023-07-27 11:30:00 +02:00
  • d2817771e5 Update README.md Nikolay Dubina 2023-07-27 14:40:21 +08:00
  • 4e23ad8399 touchups to readme: reshuffle todos, and add a windows note Andrej Karpathy 2023-07-27 06:17:13 +00:00
  • f19f50a744 stylistic changes for the windows support ifdefs Andrej Karpathy 2023-07-27 06:08:40 +00:00
  • a03ce1ee6d Merge pull request #132 from richinseattle/master Andrej 2023-07-26 23:00:33 -07:00
  • b18d325660 add windows build commands richinseattle 2023-07-26 22:58:48 -07:00
  • de6f2fc81c Merge pull request #130 from richinseattle/patch-3 Andrej 2023-07-26 22:52:14 -07:00
  • 14e90b506c Merge pull request #131 from tmc/patch-2 Andrej 2023-07-26 22:50:04 -07:00
  • 01c06fa83c readme: Include reference to go port Travis Cline 2023-07-26 22:44:15 -07:00
  • 5b405a7004 Add Windows support files with mmap impl richinseattle 2023-07-26 22:40:56 -07:00
  • 4a6b7a471d Include windows support header (for mmap) richinseattle 2023-07-26 22:40:01 -07:00
  • b7efb1b5c9 Merge branch 'richinseattle-patch-2' Andrej Karpathy 2023-07-27 05:23:49 +00:00
  • 0d18fa7780 Merge branch 'patch-2' of https://github.com/richinseattle/llama2.c into richinseattle-patch-2 Andrej Karpathy 2023-07-27 05:23:05 +00:00
  • eff1c1b425 Merge branch 'master' of github.com:karpathy/llama2.c Andrej Karpathy 2023-07-27 05:20:59 +00:00
  • 5c55d59325 Merge pull request #128 from richinseattle/patch-1 Andrej 2023-07-26 22:20:49 -07:00
  • 37e8c20f4f Windows compat: Use GetTickCount for delta timer richinseattle 2023-07-26 22:19:49 -07:00
  • b35e82f63b Merge branch 'richinseattle-patch-1' Andrej Karpathy 2023-07-27 05:18:39 +00:00
  • 815ce33569 Merge branch 'patch-1' of https://github.com/richinseattle/llama2.c into richinseattle-patch-1 Andrej Karpathy 2023-07-27 05:15:52 +00:00
  • 539dc73196 fix whitespace richinseattle 2023-07-26 22:12:32 -07:00
  • 34cce6a6b5 Merge pull request #126 from som-sama/patch-1 Andrej 2023-07-26 22:09:34 -07:00
  • 530ef8e778 light touchups to export script so one doesn't need to pass in a slash at the end Andrej Karpathy 2023-07-27 05:08:45 +00:00
  • 7f7a3b2d56 update openmp pragmas for MSVC compatibility richinseattle 2023-07-26 22:06:23 -07:00
  • 7887133145 Center align cute llama image in README Som 2023-07-27 09:26:20 +05:30
  • 5f681b64b1 oops missed a section somehow, updating readme Andrej Karpathy 2023-07-27 03:01:48 +00:00
  • c2bbe9c6fb link to the huggingface hub models instead Andrej Karpathy 2023-07-27 00:14:23 +00:00
  • 7a4ca4a98b add contributing section to readme, and also notable forks section Andrej Karpathy 2023-07-26 23:58:49 +00:00
  • 4085e8971f Merge pull request #119 from kroggen/code-comments Andrej 2023-07-26 15:50:01 -07:00
  • 57034480b6 add some code comments Bernardo Ramos 2023-07-26 19:48:14 -03:00
  • f0f43b7288 small note on traing times Andrej Karpathy 2023-07-26 22:12:50 +00:00
  • 2711ae8c32 make compiler tunable in Makefile, i think potentially nice and useful Andrej Karpathy 2023-07-26 16:40:40 +00:00
  • 7059d7dba9 Update README.md Andrej 2023-07-26 09:06:08 -07:00
  • 7496ea8108 Update README.md Andrej 2023-07-26 08:59:42 -07:00
  • f5d8797af2 Update README.md Andrej 2023-07-26 08:59:12 -07:00
  • 3aedfe59f1 Merge branch 'aegkmq-master' Andrej Karpathy 2023-07-26 15:43:06 +00:00
  • 8986005f23 Minor cleanup aegkmq 2023-07-26 16:38:42 +09:00
  • 36bf904c18 Refactor freqs_cis into freqs_cos and freqs_sin, and remove complex64 for ONNX export compatibility aidoge 2023-07-26 14:23:25 +08:00
  • 36c522a0d8 Improve locality aegkmq 2023-07-26 13:24:27 +09:00
  • f5650891d5 honestly at this point this is a lot more my nanogpt code than llama code Andrej Karpathy 2023-07-25 23:57:03 +00:00
  • 7f9f5ca853 Update README.md: new llama model export Andrej 2023-07-25 16:30:28 -07:00
  • 5bcd19a204 Merge pull request #85 from python273/export-llama-without-llama Andrej 2023-07-25 16:23:56 -07:00
  • 614bf91e5d Merge pull request #60 from emma-eva/patch-1 Andrej 2023-07-25 16:06:41 -07:00
  • 366711acf8 Merge pull request #77 from madroidmaq/master Andrej 2023-07-25 16:01:55 -07:00
  • 4d1fa2f2c6 Export llama without llama python273 2023-07-26 01:32:00 +04:00
  • ac22fbce7e Update README.md: formate output samples madroid 2023-07-26 00:40:32 +08:00
  • 6cf34d610a Update README.md Andrej 2023-07-25 08:14:48 -07:00
  • 34ccb64ed8 fix typo in readme after adding the 110m model Andrej Karpathy 2023-07-25 15:02:11 +00:00
  • 94730f1766 add the 110m model, as it finished training Andrej Karpathy 2023-07-25 15:00:57 +00:00
  • 05ee4cbf38 fix bug in timing - use steps not max seq len doh Andrej Karpathy 2023-07-25 14:21:37 +00:00
  • d359fae505 Merge pull request #69 from RichardScottOZ/patch-1 Andrej 2023-07-25 07:04:17 -07:00
  • f3a1e227fe intimately RichardScottOZ 2023-07-25 21:26:30 +09:30
  • 6ce91b1b3b Fixed time_in_ms() compile time error (termux and neoterm) Emma Eva 2023-07-25 12:12:40 +06:00
  • 98ec4ba23d Update README.md Andrej 2023-07-24 22:54:54 -07:00
  • 81c90bfcb7 Update README.md: small tweaks Andrej 2023-07-24 22:51:39 -07:00
  • cf625ecd7e Update README.md Andrej 2023-07-24 21:25:31 -07:00
  • c3e0d73bd2 we can inference Meta's Llama 2 7B, yay Andrej Karpathy 2023-07-25 04:21:07 +00:00
  • 133ad3ffff Merge pull request #50 from karpathy/memmap Andrej 2023-07-24 18:59:29 -07:00
  • a1f6b4653e merge conflict resolve with imports Andrej Karpathy 2023-07-25 01:58:46 +00:00
  • d18e9efd77 Merge pull request #48 from richinseattle/richinseattle-patch-1 Andrej 2023-07-24 16:37:37 -07:00
  • b2857c6af2 Switch to using timespec_get() for cross OS compatibility richinseattle 2023-07-24 16:31:38 -07:00
  • f121f5f0c5 Merge branch 'karpathy:master' into richinseattle-patch-1 richinseattle 2023-07-24 16:30:07 -07:00
  • cae88dfbab tune readme around timings etc Andrej Karpathy 2023-07-24 23:27:48 +00:00
  • 496466f78f add rundebug to makefile, useful for spotting issues and such Andrej Karpathy 2023-07-24 23:13:59 +00:00
  • e6e3f1322b candidate memmap implementation Andrej Karpathy 2023-07-24 22:54:49 +00:00
  • 2be7d7887b MSVC Compatibility fix for timer richinseattle 2023-07-24 15:22:20 -07:00
  • 16edfe6364 add a simple makefile Andrej Karpathy 2023-07-24 21:50:04 +00:00
  • bf9f6f2ece Add discord link to Readme Andrej 2023-07-24 14:22:29 -07:00
  • 669b75ddc8 Merge pull request #43 from krzysztof-jusiak/rmsnorm Andrej 2023-07-24 14:13:49 -07:00
  • 687473c009 Update README.md with TinyStories model series Andrej 2023-07-24 14:11:27 -07:00
  • 791be9d991 tweak argparse. fix steps=256, even if some models may support longer maximum seq_len. get rid of seed option for now, use temp=0.0 for deterministic behavior Andrej Karpathy 2023-07-24 20:59:32 +00:00
  • 90ae37c3e6 git push origin masterMerge branch 'admu-progvar-master' Andrej Karpathy 2023-07-24 20:39:40 +00:00
  • c9b1f10124 Speed up rmsnorm by using sqrtf/expf Kris Jusiak 2023-07-24 13:06:27 -05:00
  • c9ad067c5d parallelize multi-head attention Franz Louis Cesista 2023-07-25 01:10:12 +08:00
  • 50a086edde add warning about fastmath Andrej Karpathy 2023-07-24 15:18:04 +00:00
  • fff00ffd07 ack to lambda Andrej Karpathy 2023-07-24 14:31:52 +00:00
  • d0ddf94cc3 Merge pull request #36 from hu-po/patch-1 Andrej 2023-07-24 07:27:36 -07:00
  • 228c4ea3ea Merge pull request #28 from SlyEcho/master Andrej 2023-07-24 07:23:07 -07:00
  • 624cdfc76a add dropout support to model Andrej Karpathy 2023-07-24 14:18:50 +00:00
  • cdfb49208a Merge pull request #37 from awgu/pt2 Andrej 2023-07-24 07:15:40 -07:00
  • 9055766cf6 docs on how to run with openmp Andrej Karpathy 2023-07-24 14:08:06 +00:00
  • cbbe4301b0 Merge branch 'krzysztof-jusiak-openmp' Andrej Karpathy 2023-07-24 14:02:28 +00:00