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

Commit Graph

  • d47fc41b6a Merge branch 'ci-tiny-model' of https://github.com/Majdoddin/llama2.c into Majdoddin-ci-tiny-model Andrej Karpathy 2023-08-16 02:20:34 +00:00
  • ca67253f28 smallfix: not sure what the point of this indirection was Andrej Karpathy 2023-08-15 16:09:33 +00:00
  • 4c63c5608d shorten top comment on run.c file Andrej Karpathy 2023-08-15 16:07:48 +00:00
  • a47f9b3969 collapsing copy paste code because it's driving my ocd crazy Andrej Karpathy 2023-08-15 16:03:11 +00:00
  • 87b11edf27 modifiying test_all so it can safely run on windows Ruhollah Majdoddin 2023-08-15 16:01:53 +00:00
  • 66c9f5e6c8 Adding pytest with the tiny model to macOS and windows (except amd64_arm64) runners Ruhollah Majdoddin 2023-08-15 15:58:04 +00:00
  • 88eb238255 add tests into Makefile convenience Andrej Karpathy 2023-08-15 15:57:27 +00:00
  • 600cedb33d Merge pull request #297 from karpathy/feature/utf8 Andrej 2023-08-14 19:54:49 -07:00
  • fe2de68688 fix sample.py from tokenizer changes before Andrej Karpathy 2023-08-15 02:33:01 +00:00
  • a9a0628c92 thoroughly commented the UTF-8 byte reading code Andrej Karpathy 2023-08-15 02:18:49 +00:00
  • d459fd4243 add back careful processing of the byte tokens Andrej Karpathy 2023-08-15 01:42:33 +00:00
  • 4bf36ecc17 get rid of the special byte decoding logic Andrej Karpathy 2023-08-15 01:04:10 +00:00
  • 8417cb438d Merge branch 'utf8' of https://github.com/atamurad/llama2.c into feature/utf8 Andrej Karpathy 2023-08-15 00:18:53 +00:00
  • 94a3a5e0a5 Merge branch 'master' of github.com:karpathy/llama2.c Andrej Karpathy 2023-08-14 14:52:15 +00:00
  • 32c1ff97fb missed p->dim to kv_dim for k,v vectors. we're not doing anything wrong we're just being wasteful with memory. thanks @xefoci7612 for pointing out Andrej Karpathy 2023-08-14 14:52:07 +00:00
  • 013e012b87 Merge pull request #286 from Nick-infinity/master Andrej 2023-08-14 07:46:39 -07:00
  • 50f970d170 Merge pull request #289 from chenyangMl/update_readme Andrej 2023-08-14 07:41:13 -07:00
  • 2a9a4c4e14 update readme wiht a simple line to introduce llama2.c-zh chenyang 2023-08-14 15:12:30 +08:00
  • 79900ff68e update readme wiht a simple line to introduce llama2.c-zh chenyang 2023-08-14 15:00:33 +08:00
  • eec9ad5a5b Merge remote-tracking branch 'upstream/master' Krishnaraj Bhat 2023-08-14 12:02:40 +05:30
  • 82ad2ba34e remove tiktoken as dependency Andrej Karpathy 2023-08-14 05:53:57 +00:00
  • c39f19f1a9 [Feat]: Add support for meta llama hf model conversion Nikhil Gupta 2023-08-14 10:18:51 +05:30
  • bae0bcf484 Small tweaks to Readme intro Andrej 2023-08-13 20:03:00 -07:00
  • 45afa91dca the accum function has been bothering me, there is no real need to add a function here, it does something trivial and is only used twice, scrap Andrej Karpathy 2023-08-14 02:54:27 +00:00
  • 854c97b660 turn topp 0.9 back on by default thanks to recent PR contributions truncating before quicksort Andrej Karpathy 2023-08-14 00:12:45 +00:00
  • 4a2c375df9 Merge pull request #276 from jrudolph/improve-top-p Andrej 2023-08-13 17:05:38 -07:00
  • b3d6a9e6b5 Merge pull request #285 from karpathy/feature/civ2 Andrej 2023-08-13 16:55:01 -07:00
  • 091c799653 Merge branch 'master' into feature/civ2 Andrej 2023-08-13 16:54:24 -07:00
  • c970f69334 oops i should probably call this function lol Andrej Karpathy 2023-08-13 23:48:01 +00:00
  • 223a67048a add optional manual dispatch of actions Andrej Karpathy 2023-08-13 23:39:37 +00:00
  • 86325bf7e8 attempt to upgrade the CI to run our pytest Andrej Karpathy 2023-08-13 23:35:29 +00:00
  • b51c63b9f2 Merge pull request #283 from wizzard0/wizzard0-mention-1 Andrej 2023-08-13 14:36:10 -07:00
  • 8506036185 remove 'revive tests' as a todo from the readme Andrej Karpathy 2023-08-13 21:23:27 +00:00
  • f0024cfc88 revive tests. now that we have a tiny stories260K model this only requires a 2MB download. phew Andrej Karpathy 2023-08-13 21:22:44 +00:00
  • 0805cb2c31 tiny whitespace fix to try to eliminate scrollbar Andrej 2023-08-13 13:40:09 -07:00
  • b2cce341e0 oops typo fix in readme Andrej 2023-08-13 13:39:12 -07:00
  • 3e989e21f2 link to stories260K model Andrej Karpathy 2023-08-13 20:38:05 +00:00
  • 58075b5ac5 update API of sample.py to be better, small changes here Andrej Karpathy 2023-08-13 20:31:32 +00:00
  • 36b54321e5 bugfix: allocate +1 in tokens buffer for dummy whitespace atamyrat 2023-08-13 23:23:32 +03:00
  • 1bcb2d18d6 Merge pull request #284 from karpathy/feature/customtokenizer Andrej 2023-08-13 12:38:06 -07:00
  • 38bfac90a8 bigchange: add multiquery support in run.c. we can now train and inference multiquery models (where n_kv_heads < n_heads). this also means that we, in principle, support Llama 2 34B and 70B models, which are multiquery Andrej Karpathy 2023-08-13 19:34:05 +00:00
  • b28c1e26c5 Merge pull request #275 from icppWorld/webassembly-internet-computer Andrej 2023-08-13 10:14:39 -07:00
  • 5295cbb821 Merge pull request #281 from lintian06/original_llama2 Andrej 2023-08-13 10:14:00 -07:00
  • 12dec61fbf Merge pull request #282 from mihainadas/master-1 Andrej 2023-08-13 10:13:08 -07:00
  • 0e6213c6e0 Mention I can run the full 7B model Oleksandr Nikitin 2023-08-13 20:02:34 +03:00
  • 1d68a36d14 Add TypeScript port Oleksandr Nikitin 2023-08-13 19:10:07 +03:00
  • 570789aa04 Fixes https://github.com/karpathy/llama2.c/issues/280 Mihai Nadăș 2023-08-13 17:49:10 +03:00
  • 27adb082f1 Update README.md Tian Lin 2023-08-13 21:58:14 +08:00
  • daa9fd9b8a sort vocabulary for faster lookup with bsearch() atamyrat 2023-08-12 23:12:35 +03:00
  • 8b472ded1f Merge pull request #272 from karpathy/feature/customtokenizer Andrej 2023-08-12 20:31:21 -07:00
  • 9ff459b925 todo changes Andrej Karpathy 2023-08-13 03:24:31 +00:00
  • 1d14cb8dd8 add note about 4096 vs 32000 token size on tinystories Andrej Karpathy 2023-08-13 03:19:35 +00:00
  • fe49eb222c readme for custom tokenizers Andrej Karpathy 2023-08-13 03:16:18 +00:00
  • 9c3cfb46a3 make default be the llama2 tokenizer Andrej Karpathy 2023-08-13 03:08:07 +00:00
  • 00a61dc7f9 remove the tinyshakespeare dataset until i can bring it back later in a nicer form, otherwise right now we just have a ton of copy paste code here Andrej Karpathy 2023-08-13 02:18:30 +00:00
  • f5fc0c245f final piece: run.c support for new tokenizer, super ez Andrej Karpathy 2023-08-13 02:12:13 +00:00
  • ea4cedc588 add ability to export custom tokenizer to .bin format for run.c file Andrej Karpathy 2023-08-13 02:00:19 +00:00
  • d421a95b2b optimize sample_topp by filtering out small value elements up front Johannes Rudolph 2023-08-12 20:31:19 +02:00
  • b0cfa2458d ok i can train and sample a model with a custom tokenizer Andrej Karpathy 2023-08-11 16:47:29 +00:00
  • f96c7afb2d Notable fork section for WebAssembly icpp 2023-08-11 10:11:32 -04:00
  • 4c6f0af9ff add the ability to train a custom sentencepiece tokenizer with a given vocab_size, and pretok with it. some more changes still needed to merge this branch, in train.py and ofc run.c. did this in a sadly bit ugly, but fully backwards compatible way. basically when we use custom tokenizer we create a whole new directory structure for that Andrej Karpathy 2023-08-11 03:58:22 +00:00
  • c42641205f turn off topp sampling by default because it is a bit too slow to be the default. it is likely that turning it on, e.g. -p 0.9 is midlly higher quality and safer samples, but this comes at a cost of too much performance in double digit percent sometimes, for it to be on by default i think... Andrej Karpathy 2023-08-10 15:23:05 +00:00
  • d0309ab2d4 add avx2 intrinsics maybe feature/avx2 Andrej Karpathy 2023-08-10 15:01:53 +00:00
  • 46d7a6b6c6 Merge branch 'karpathy:master' into master Krishnaraj Bhat 2023-08-10 11:06:19 +05:30
  • d45a36cdd2 Update readme for openmp on mac Krishnaraj Bhat 2023-08-10 10:59:39 +05:30
  • 3f69c6cdc4 change the default to use runfast, which imo works just fine Andrej Karpathy 2023-08-10 05:06:49 +00:00
  • 5f8068fd43 Merge pull request #260 from madroidmaq/master Andrej 2023-08-09 22:03:36 -07:00
  • f60285ee78 Merge pull request #264 from trrahul/master Andrej 2023-08-09 22:00:23 -07:00
  • 04121d1b85 Merge pull request #256 from rdentato/patch-rng-seed Andrej 2023-08-09 21:56:07 -07:00
  • 256e7f885b Added C# port information in readme Rahul TR 2023-08-09 17:59:47 +05:30
  • e36e3fb50d Merge branch 'master' of github.com:karpathy/llama2.c Andrej Karpathy 2023-08-09 02:08:37 +00:00
  • 96873b0274 refine todos section make more concrete and sort Andrej Karpathy 2023-08-09 02:08:33 +00:00
  • 9713609023 Add Colab GUI: select model/temperature/prompt/etc madroid 2023-08-08 19:10:45 +08:00
  • 27c5fc76b1 Add Google Colab button madroid 2023-08-08 01:50:19 +08:00
  • 57ca3c0401 Add run.ipynb for easier feel the magic madroid 2023-08-08 01:28:07 +08:00
  • c02865df30 prompt tokenizer improvements: utf8 support, add_dummy_prefix and byte_fallback options to match sentencepiece atamyrat 2023-08-04 04:18:20 +03:00
  • ff6a2f0a7a Reset the #include <omp.h> rdentato 2023-08-07 07:28:03 +00:00
  • e49c16caa5 Changed how rng_seed is handled. Now 0 is treated as time(NULL). rdentato 2023-08-07 06:51:57 +00:00
  • 2e5fad83da Merge branch 'karpathy:master' into master Remo Dentato 2023-08-07 07:57:42 +02:00
  • 3c3b19b14c Merge pull request #242 from tairov/llama2-py Andrej 2023-08-06 19:51:30 -07:00
  • f4f4cae4cb Merge pull request #241 from danielgrittner/master Andrej 2023-08-06 19:51:13 -07:00
  • 09de2cc4ca Merge pull request #250 from npinto/master-1 Andrej 2023-08-06 18:43:01 -07:00
  • 98b515e44d FIX: model.generate() Nicolas Pinto 2023-08-06 14:48:47 -07:00
  • 999b1bf776 Added conditinal include of the OpenMP header. rdentato 2023-08-06 21:07:09 +00:00
  • 2297d158e3 Fix link to a github profile Aydyn Tairov 2023-08-06 21:47:05 +01:00
  • 512f039d5d Merge branch 'master' into master Daniel Grittner 2023-08-06 19:55:43 +02:00
  • 6734eaeff5 Rebase chanes to master Aydyn Tairov 2023-08-06 18:47:05 +01:00
  • 7178facb75 Rebase changes to master Aydyn Tairov 2023-08-06 18:45:47 +01:00
  • a7a3aa09b8 Merge branch 'master' of github.com:karpathy/llama2.c Andrej Karpathy 2023-08-06 16:33:36 +00:00
  • 79791f39b4 let's start respecting the BOS token. Don't print it explicitly, and terminate sequence if it appears. This makes sense especially after the recent addition of prompting. Also be careful with timings and making sure they come out right if we exit early in this data-dependent manner Andrej Karpathy 2023-08-06 16:33:23 +00:00
  • 4e8a3e8d5d fix style issue space with stderr printing Andrej Karpathy 2023-08-06 15:51:58 +00:00
  • 7af81ded7e Merge pull request #244 from madroidmaq/master Andrej 2023-08-06 08:43:24 -07:00
  • a25958fd45 Merge pull request #245 from rdentato/patch-stderr Andrej 2023-08-06 08:42:09 -07:00
  • 1f53735d12 Merge branch 'karpathy:master' into master Madroid Ma 2023-08-06 18:18:36 +08:00
  • 9cfb7efb85 Changed all the printf() for error/info messages so that they print on stderr. rdentato 2023-08-06 09:53:02 +00:00
  • baefaaaf76 Update README.md: add notable forks author's link madroid 2023-08-06 17:42:31 +08:00
  • fcb4cdef8b add a Rust port Daniel Grittner 2023-08-06 10:44:48 +02:00
  • 623894f5da fix bug, have to use raw_model not model to access the loss Andrej Karpathy 2023-08-06 07:55:46 +00:00
  • 65b0846637 error on seed=0 Andrej Karpathy 2023-08-06 07:31:21 +00:00
  • 8931d5092e add nucleus sampling. it costs lines of code, but i think thit is the default best way to sample, so it is important to have Andrej Karpathy 2023-08-06 07:22:39 +00:00