vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Commit graph

  • c3b2306b18
         Makefile: slightly cleanup for Mac Intel; echo instead of run ./main -h (#335) Qingyou Meng 2023-03-21 23:44:11 +08:00
  • 975d2cebf9
         cmdline option for custom amount of model parts (--n_parts N) (#348) anzz1 2023-03-21 17:42:43 +02:00
  • c92cf7c48f
         Merge branch 'master' into llama-patch-n-parts Georgi Gerganov 2023-03-21 17:41:36 +02:00
  • fe28721203
         Update main.cpp Georgi Gerganov 2023-03-21 17:40:17 +02:00
  • e0ffc861fa
         Update IPFS links to quantized alpaca with new tokenizer format (#352) Kevin Kwok 2023-03-21 08:34:49 -07:00
  • 8f644a0a85
         Change default repeat_penalty to 1.0 Georgi Gerganov 2023-03-21 17:32:14 +02:00
  • eb34620aec
         Add tokenizer test + revert to C++11 (#355) Georgi Gerganov 2023-03-21 17:29:41 +02:00
  • a0d00bd809
         Revert back to C++11, avoid std::string_view in the tokenizer Georgi Gerganov 2023-03-21 11:34:58 +02:00
  • a19aa63ba2
         renamed token to tok Fabio Rossini Sluzala 2023-03-21 11:54:04 -03:00
  • 2e664f1ff4
         Add initial AVX512 support for dot product on Linux (#320) master-2e664f1 Casey Primozic 2023-03-21 07:35:42 -07:00
  • 35ae689f78 Add timing/ETA Gary Linscott 2023-03-21 07:29:23 -07:00
  • 2f8ab68d72 Output all perplexitiies Gary Linscott 2023-03-21 07:10:42 -07:00
  • 7e6f4ed5e2 use a portable exit function Concedo 2023-03-21 22:00:27 +08:00
  • a1625c4be1 changed file embedding technique Concedo 2023-03-21 21:16:06 +08:00
  • 91e2b43575 Merge remote-tracking branch 'origin/master' into concedo Concedo 2023-03-21 20:48:56 +08:00
  • f7e3a33f4e
         Update IPFS links to quantized alpaca with new tokenizer format Kevin Kwok 2023-03-21 05:41:59 -07:00
  • ff1c0c4898 added embedded copy of kobold lite Concedo 2023-03-21 20:41:19 +08:00
  • 11d84b2ed9
         Revert back to C++11 Georgi Gerganov 2023-03-21 11:34:58 +02:00
  • ecd982ddc0
         Add tokenizer unit test + vocab-only data for tests Georgi Gerganov 2023-03-21 11:27:25 +02:00
  • 0fbf4b61ab
         Support -ins for alpaca model in tcp server vonjackustc 2023-03-21 17:32:00 +08:00
  • db8d0f1798 Move AVX512 dot product block helper closer to caller Casey Primozic 2023-03-21 01:38:38 -07:00
  • 05f2f48f70
         Split AVX512 process one block function out from inline Casey Primozic 2023-03-21 01:36:30 -07:00
  • b839231337
         cmdline option for custom amount of model parts (--n_parts N) anzz1 2023-03-21 10:25:46 +02:00
  • 7636ddb9e4
         Update README.md Kevin Kwok 2023-03-20 22:16:27 -07:00
  • 8009a8ddb0 Inject the reverse prompt again after eos in interactive mode Slaren 2023-03-21 04:56:47 +01:00
  • 8cf9f34edd
         Adding missing features of CMakeLists.txt & Refactoring (#131) master-8cf9f34 nusu-github 2023-03-21 09:37:16 +09:00
  • 1d7a1a785f Add missing permutation. Now it works. comex 2023-03-20 17:33:11 -07:00
  • 34596530b2
         Nest struct token score inside gpt_vocab Fabio Rossini Sluzala 2023-03-20 21:28:14 -03:00
  • 76af3f5a64
         Re-use existing bytesFromNibbles function Casey Primozic 2023-03-20 15:55:42 -07:00
  • 2479c78bc6
         alternate approach to replace end of text tokens rabidcopy 2023-03-20 17:45:52 -05:00
  • bd4b46d6ba Nix flake: set meta.mainProgram to llama Ben Siraphob 2023-03-20 16:44:30 -05:00
  • 8793e7ec64 fix: win map fixes, still not working oKatanaaa 2023-03-21 01:46:44 +04:00
  • 47687dbe3d
         Nix flake: set meta.mainProgram to llama Ben Siraphob 2023-03-20 16:44:30 -05:00
  • b6fdbee3de
         Implement TCP server mode. Thiago Padilha 2023-03-18 23:30:53 -03:00
  • 9ed33b37de
         Remove direct access to std streams from llama_main Thiago Padilha 2023-03-18 12:20:20 -03:00
  • 8b9a9dc49f
         Move model loading back to main.cpp Thiago Padilha 2023-03-18 12:12:00 -03:00
  • 734a858ad5
         Add main.cpp back, and invoke llama_main from it Thiago Padilha 2023-03-18 11:58:11 -03:00
  • 6864a1f8e2
         Move struct definitions in llama.cpp to llama.h Thiago Padilha 2023-03-18 11:52:55 -03:00
  • 95c6748913
         Move main.cpp to llama.cpp Thiago Padilha 2023-03-18 11:49:09 -03:00
  • d9284a580c
         only print manual newline with reverse prompt rabidcopy 2023-03-20 15:50:01 -05:00
  • 466073896b
         print a new line on end of text in interactive rabidcopy 2023-03-20 15:13:10 -05:00
  • ac6a9d9717
         cleanup whitespace rabidcopy 2023-03-20 14:37:27 -05:00
  • 94edeaf7df
         relocate previous newline token const rabidcopy 2023-03-20 14:35:36 -05:00
  • 6b6d5b5024
         Fixed tokenizer.model not found error when model dir is symlink (#325) Qingyou Meng 2023-03-21 03:33:10 +08:00
  • a791a68b61
         move file magic/version to header, print expected version (#319) master-a791a68 Mack Straight 2023-03-20 12:26:01 -07:00
  • 3eca29ec0d
         dynamically determine newline token rabidcopy 2023-03-20 14:02:48 -05:00
  • 330b86eed2
         Make newline token a constant rabidcopy 2023-03-20 13:02:54 -05:00
  • e671ad534e
         Merge branch 'ggerganov:master' into master Qingyou Meng 2023-03-21 02:00:56 +08:00
  • e949eb518f Makefile: slightly cleanup for Mac Intel; echo instead of run ./main -h mqy 2023-03-21 01:11:25 +08:00
  • 0f1b21cb90
         Docker - Fix publish docker image in GitHub Registry (#235) master-0f1b21c Bernat Vadell 2023-03-20 18:05:20 +01:00
  • 4fe9734e09
         Improve interactive mode's coherence after EOS rabidcopy 2023-03-20 11:33:50 -05:00
  • 0cc13a2193 add alpaca support into docker scripts Bernat Vadell 2023-03-20 16:58:53 +01:00
  • 8d39365af6 update license, added backwards compatibility with both ggml model formats, fixed context length issues. Concedo 2023-03-20 23:43:35 +08:00
  • 98b31b789c try to fix docker pipeline using as password github_token & username repository_owner Bernat Vadell 2023-03-20 16:32:52 +01:00
  • 12280807c3 Remove unnecessary use of std::stringstream. Johnman 2023-03-20 16:31:10 +01:00
  • 9d7a993d81
         Change the version to 3.12 nusu-github 2023-03-21 00:27:10 +09:00
  • 6242d1ccd5 Cleanup. Johnman 2023-03-20 16:15:00 +01:00
  • e9f77473dc
         Update main.cpp tjohnman 2023-03-20 16:10:26 +01:00
  • b646ffa1b1 Check for reverse prompt by characters instead of tokens (#292) Johnman 2023-03-20 16:06:58 +01:00
  • bc53fc0cd6
         Reflects C/C++ standard individually nusu-github 2023-03-20 23:39:12 +09:00
  • d1fa8f5833 Merge remote-tracking branch 'origin/master' into perplexity Gary Linscott 2023-03-20 07:17:13 -07:00
  • d824baa37f
         C++11 to C++17 nusu-github 2023-03-20 22:28:47 +09:00
  • a2c10e0d2f Merge branch 'master' into concedo Concedo 2023-03-20 20:58:27 +08:00
  • ef792ae8bd
         Merge unordered_map/vector changes with trunk updates Fabio Rossini Sluzala 2023-03-20 09:36:21 -03:00
  • d91896a069 Fixed tokenizer.model not found error when model dir is symlink mqy 2023-03-20 20:33:58 +08:00
  • 03755743cf log distribution after prompt tokens Maël Kerbiriou 2023-03-16 18:58:59 +01:00
  • 4547848743 log llama's entropy Maël Kerbiriou 2023-03-20 12:15:13 +01:00
  • a6598801ad
         Add initial AVX512 support for dot product on Linux Casey Primozic 2023-03-20 04:15:40 -07:00
  • e66962ff63 log file for debug output Maël Kerbiriou 2023-03-20 12:15:01 +01:00
  • aa6c2bd5d2 sampler log function Maël Kerbiriou 2023-03-16 18:12:17 +01:00
  • abbf7e7a61 new sampler for experimentation. Maël Kerbiriou 2023-03-16 16:52:02 +01:00
  • 99f3908c51
         Automatically Generate Releases for Mac, Linux, Windows (#81) Kevin Kwok 2023-03-20 03:41:11 -07:00
  • 4aa7d2a3f8 move file magic/version to header, print expected version Mack Straight 2023-03-20 03:32:26 -07:00
  • 4655634627 fix typo in comment Mack Straight 2023-03-20 03:22:55 -07:00
  • 074bea2eb1
         sentencepiece bpe compatible tokenizer (#252) master-074bea2 Mack Straight 2023-03-20 03:17:23 -07:00
  • 649cee5f62 sentencepiece bpe compatible tokenizer Mack Straight 2023-03-17 20:02:44 -07:00
  • 5cb63e2493
         Add tqdm to Python requirements (#293) Stephan Walter 2023-03-20 08:24:11 +00:00
  • f128838e1c remove workflows Concedo 2023-03-20 15:57:55 +08:00
  • 0e83240e0f
         Windows build Fix nusu-github 2023-03-20 16:37:00 +09:00
  • 2fc5266568 Add OpenBSD support Kevin Lo 2023-03-20 13:45:26 +08:00
  • dda69d4034 bugfixes Concedo 2023-03-20 13:37:51 +08:00
  • 564cdf8f4b
         Merge branch 'ggerganov:master' into master OvJat 2023-03-20 11:36:24 +08:00
  • 5880a9d788 Fix color codes emitting mid-UTF8 code. Matvey Soloviev 2023-03-20 02:51:11 +01:00
  • 2cbe79694a
         Merge pull request #76 from anzz1/patch-3 Kevin Kwok 2023-03-19 18:46:14 -07:00
  • e83984f583
         add cached torrent links anzz1 2023-03-20 02:31:42 +02:00
  • b37e0950db
         Do not call SetConsoleMode if the mode is already set anzz1 2023-03-20 02:02:29 +02:00
  • 1c545e51ed Update llama_model_load() from master branch Thomas Antony 2023-03-19 16:59:17 -07:00
  • 0fed2ab999
         Enable ANSI colors on Windows 10+ anzz1 2023-03-20 01:52:36 +02:00
  • 5d79c5b985
         Update main.Dockerfile PGTBoos 2023-03-19 23:48:09 +01:00
  • fbff268461 Don't let remaining_tokens get larger than the context. Johnman 2023-03-19 23:38:52 +01:00
  • 40ab4861cc
         Removed include <map> Fabio Rossini Sluzala 2023-03-19 19:32:51 -03:00
  • dd459b604f Reset token budget after every user intervention. Johnman 2023-03-19 22:59:16 +01:00
  • 78b964eb1e
         fix last commit on gpt_vocab_init add vocab.id_to_token.resize(vocab.token_to_id.size()); Fabio Rossini Sluzala 2023-03-19 18:55:09 -03:00
  • da5303c1ea
         bugfix: default should not be interactive (#304) master-da5303c cocktailpeanut 2023-03-19 17:44:20 -04:00
  • 25ef27c6bc
         Improve performance by changing std::map to std::unordered_map and std::map<id, token> id_to_token; to std::vector<token> id_to_token; Fabio Rossini Sluzala 2023-03-19 18:38:42 -03:00
  • 55be2120b1 bugfix: default should not be interactive cocktailpeanut 2023-03-19 17:22:11 -04:00
  • 5195fed013 Add support for multiple antiprompts Thomas Antony 2023-03-19 13:39:06 -07:00
  • abb82a06a5 Merge remote-tracking branch 'origin/master' into perplexity Gary Linscott 2023-03-19 13:37:57 -07:00
  • 91d71fe0c1 More accurate perplexity calculation - over all logits in the context window (so 512x more tokens!) Gary Linscott 2023-03-19 13:33:12 -07:00
  • b3541ceb65 Update CMakeLists to rename targets Thomas Antony 2023-03-19 13:20:12 -07:00