ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-03 10:30:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 40ea807a97 Add details on perplexity to README.md (#395) Gary Linscott 2023-03-22 08:53:54 -07:00
  • 75ec4e0d8c Add missing header for memcpy (#386) Yusuf Kağan Hanoğlu 2023-03-22 11:55:45 +03:00
  • d5850c53ca Add missing header for memcpy (#386) Yusuf Kağan Hanoğlu 2023-03-22 11:55:45 +03:00
  • dc2abfbdf0 When seed <= 0 - use the clock to generate one Georgi Gerganov 2023-03-22 07:47:15 +02:00
  • ae44e23ee3 When seed <= 0 - use the clock to generate one Georgi Gerganov 2023-03-22 07:47:15 +02:00
  • 5d0d8f903c Init llama_context_params properly from CLI (#370) Georgi Gerganov 2023-03-22 07:45:00 +02:00
  • 928480ef5b Init llama_context_params properly from CLI (#370) Georgi Gerganov 2023-03-22 07:45:00 +02:00
  • 1deed1f1e7 Remove temporary notice and update hot topics Georgi Gerganov 2023-03-22 07:34:02 +02:00
  • 56817b1f88 Remove temporary notice and update hot topics Georgi Gerganov 2023-03-22 07:34:02 +02:00
  • c40b5b3d59 Introduce C-style API (#370) Georgi Gerganov 2023-03-22 07:32:36 +02:00
  • f5a77a629b Introduce C-style API (#370) Georgi Gerganov 2023-03-22 07:32:36 +02:00
  • 3081cf8ed9 Add SHA256SUMS file and instructions to README how to obtain and verify the downloads Gary Mulder 2023-03-20 20:14:06 +00:00
  • da0e9fe90c Add SHA256SUMS file and instructions to README how to obtain and verify the downloads Gary Mulder 2023-03-20 20:14:06 +00:00
  • f4a4251f0e Fix bin dir for win ci anzz1 2023-03-21 23:49:24 +02:00
  • e6c9e0986c Fix bin dir for win ci anzz1 2023-03-21 23:49:24 +02:00
  • 3d3d0d2fe5 specify build type for ctest on windows (#371) Erik Scholz 2023-03-21 22:34:25 +01:00
  • 01a297b099 specify build type for ctest on windows (#371) Erik Scholz 2023-03-21 22:34:25 +01:00
  • 278d9b3d84 Add notice about pending change Georgi Gerganov 2023-03-21 22:57:35 +02:00
  • 3366853e41 Add notice about pending change Georgi Gerganov 2023-03-21 22:57:35 +02:00
  • 410097f4c8 fix typo in chatLLaMa (#368) Mathieu Nayrolles 2023-03-21 16:52:27 -04:00
  • 3f9c6135e4 fix typo in chatLLaMa (#368) Mathieu Nayrolles 2023-03-21 16:52:27 -04:00
  • b115c2f104 Update issue templates Georgi Gerganov 2023-03-21 19:47:27 +02:00
  • 0f61352708 Update issue templates Georgi Gerganov 2023-03-21 19:47:27 +02:00
  • edb2b84e60 We could use std::unordered_map over std::map (#305) Fabio R. Sluzala 2023-03-21 14:21:50 -03:00
  • 353ec251a4 We could use std::unordered_map over std::map (#305) Fabio R. Sluzala 2023-03-21 14:21:50 -03:00
  • 5b330f1320 Fix color codes emitting mid-UTF8 code. (#312) Matvey Soloviev 2023-03-21 18:11:01 +01:00
  • 89d5d90f3b Fix color codes emitting mid-UTF8 code. (#312) Matvey Soloviev 2023-03-21 18:11:01 +01:00
  • bbc3cd7558 Importer for GPTQ quantized LLaMA models (#301) comex 2023-03-21 09:42:25 -07:00
  • 16ffc013c6 Importer for GPTQ quantized LLaMA models (#301) comex 2023-03-21 09:42:25 -07:00
  • 4458de7520 Compute perplexity over prompt (#270) Gary Linscott 2023-03-21 09:27:42 -07:00
  • 486ae645fd Compute perplexity over prompt (#270) Gary Linscott 2023-03-21 09:27:42 -07:00
  • 6b596e4215 Add chatLLaMa script (#198) Jean-Christophe Hoelt 2023-03-21 18:23:15 +02:00
  • 3ab3e6582f Add chatLLaMa script (#198) Jean-Christophe Hoelt 2023-03-21 18:23:15 +02:00
  • eff5726e38 makefile: Fix CPU feature detection on Haiku (#218) Alex von Gluck IV 2023-03-21 11:21:06 -05:00
  • f157088cb7 makefile: Fix CPU feature detection on Haiku (#218) Alex von Gluck IV 2023-03-21 11:21:06 -05:00
  • 1afe9491f6 Enable ANSI colors on Windows 10+ (#311) anzz1 2023-03-21 18:14:46 +02:00
  • c86ba036e6 Enable ANSI colors on Windows 10+ (#311) anzz1 2023-03-21 18:14:46 +02:00
  • e7a75316dc Minor style changes Georgi Gerganov 2023-03-21 18:10:32 +02:00
  • 1daf4dd712 Minor style changes Georgi Gerganov 2023-03-21 18:10:32 +02:00
  • f57b30a8e1 Add chat.sh script Georgi Gerganov 2023-03-21 18:09:37 +02:00
  • dc6a845b85 Add chat.sh script Georgi Gerganov 2023-03-21 18:09:37 +02:00
  • 2a443114ff Check for reverse prompt by characters instead of tokens (#292) (#330) tjohnman 2023-03-21 17:05:06 +01:00
  • 6a612959e1 Check for reverse prompt by characters instead of tokens (#292) (#330) tjohnman 2023-03-21 17:05:06 +01:00
  • f571f4b61c Check for reverse prompt by characters instead of tokens (#292) (#330) tjohnman 2023-03-21 17:04:43 +01:00
  • d5f56a5e5a Check for reverse prompt by characters instead of tokens (#292) (#330) tjohnman 2023-03-21 17:04:43 +01:00
  • 614b1afa1c Fix convert script, warnings alpaca instructions, default params Georgi Gerganov 2023-03-21 17:59:16 +02:00
  • 3bfa3b43b7 Fix convert script, warnings alpaca instructions, default params Georgi Gerganov 2023-03-21 17:59:16 +02:00
  • f2222d00b1 Add OpenBSD support (#314) Kevin Lo 2023-03-21 09:50:09 -06:00
  • 715d292ee0 Add OpenBSD support (#314) Kevin Lo 2023-03-21 09:50:09 -06:00
  • bcf96da81a fix typo in comment (#318) Mack Straight 2023-03-21 08:49:43 -07:00
  • c98ae02668 fix typo in comment (#318) Mack Straight 2023-03-21 08:49:43 -07:00
  • ec57365b4f Makefile: slightly cleanup for Mac Intel; echo instead of run ./main -h (#335) Qingyou Meng 2023-03-21 23:44:11 +08:00
  • c3b2306b18 Makefile: slightly cleanup for Mac Intel; echo instead of run ./main -h (#335) Qingyou Meng 2023-03-21 23:44:11 +08:00
  • a2c6b64d8d cmdline option for custom amount of model parts (--n_parts N) (#348) anzz1 2023-03-21 17:42:43 +02:00
  • 975d2cebf9 cmdline option for custom amount of model parts (--n_parts N) (#348) anzz1 2023-03-21 17:42:43 +02:00
  • 9c26af616b Update IPFS links to quantized alpaca with new tokenizer format (#352) Kevin Kwok 2023-03-21 08:34:49 -07:00
  • e0ffc861fa Update IPFS links to quantized alpaca with new tokenizer format (#352) Kevin Kwok 2023-03-21 08:34:49 -07:00
  • de8241445c Change default repeat_penalty to 1.0 Georgi Gerganov 2023-03-21 17:32:14 +02:00
  • 8f644a0a85 Change default repeat_penalty to 1.0 Georgi Gerganov 2023-03-21 17:32:14 +02:00
  • 26d3089d76 Add tokenizer test + revert to C++11 (#355) Georgi Gerganov 2023-03-21 17:29:41 +02:00
  • eb34620aec Add tokenizer test + revert to C++11 (#355) Georgi Gerganov 2023-03-21 17:29:41 +02:00
  • de601697f3 Add initial AVX512 support for dot product on Linux (#320) Casey Primozic 2023-03-21 07:35:42 -07:00
  • 2e664f1ff4 Add initial AVX512 support for dot product on Linux (#320) Casey Primozic 2023-03-21 07:35:42 -07:00
  • a4007328a5 Adding missing features of CMakeLists.txt & Refactoring (#131) nusu-github 2023-03-21 09:37:16 +09:00
  • 8cf9f34edd Adding missing features of CMakeLists.txt & Refactoring (#131) nusu-github 2023-03-21 09:37:16 +09:00
  • bc283200bd Nix flake: set meta.mainProgram to llama Ben Siraphob 2023-03-20 16:44:30 -05:00
  • bd4b46d6ba Nix flake: set meta.mainProgram to llama Ben Siraphob 2023-03-20 16:44:30 -05:00
  • fe2c4d189c Fixed tokenizer.model not found error when model dir is symlink (#325) Qingyou Meng 2023-03-21 03:33:10 +08:00
  • 6b6d5b5024 Fixed tokenizer.model not found error when model dir is symlink (#325) Qingyou Meng 2023-03-21 03:33:10 +08:00
  • 1130f96c88 move file magic/version to header, print expected version (#319) Mack Straight 2023-03-20 12:26:01 -07:00
  • a791a68b61 move file magic/version to header, print expected version (#319) Mack Straight 2023-03-20 12:26:01 -07:00
  • 30c583d35a Docker - Fix publish docker image in GitHub Registry (#235) Bernat Vadell 2023-03-20 18:05:20 +01:00
  • 0f1b21cb90 Docker - Fix publish docker image in GitHub Registry (#235) Bernat Vadell 2023-03-20 18:05:20 +01:00
  • 60d93896be sentencepiece bpe compatible tokenizer (#252) Mack Straight 2023-03-20 03:17:23 -07:00
  • 074bea2eb1 sentencepiece bpe compatible tokenizer (#252) Mack Straight 2023-03-20 03:17:23 -07:00
  • a5d8a1a459 Add tqdm to Python requirements (#293) Stephan Walter 2023-03-20 08:24:11 +00:00
  • 5cb63e2493 Add tqdm to Python requirements (#293) Stephan Walter 2023-03-20 08:24:11 +00:00
  • b80cecdcc4 bugfix: default should not be interactive (#304) cocktailpeanut 2023-03-19 17:44:20 -04:00
  • da5303c1ea bugfix: default should not be interactive (#304) cocktailpeanut 2023-03-19 17:44:20 -04:00
  • b41982fb59 Rename script Georgi Gerganov 2023-03-19 21:58:51 +02:00
  • 4545539d71 Rename script Georgi Gerganov 2023-03-19 21:58:51 +02:00
  • b3ce128780 Add temporary helper script for Alpaca chat Georgi Gerganov 2023-03-19 21:57:28 +02:00
  • edeba28366 Add temporary helper script for Alpaca chat Georgi Gerganov 2023-03-19 21:57:28 +02:00
  • fa0645a55c fix coloring of last n_batch of prompt, and refactor line input (#221) Rickey Bowers Jr 2023-03-19 13:44:30 -06:00
  • 5c19c70ba6 fix coloring of last n_batch of prompt, and refactor line input (#221) Rickey Bowers Jr 2023-03-19 13:44:30 -06:00
  • 3a9d372c08 Support for multiple reverse prompts. (#299) tjohnman 2023-03-19 20:33:06 +01:00
  • 24568371ae Support for multiple reverse prompts. (#299) tjohnman 2023-03-19 20:33:06 +01:00
  • 3eaf221dee Improved quantize script (#222) Suaj Carrot 2023-03-19 12:38:44 -06:00
  • 7392f1cd2c Improved quantize script (#222) Suaj Carrot 2023-03-19 12:38:44 -06:00
  • eacfb91e66 Make prompt randomization optional. (#300) tjohnman 2023-03-19 19:36:19 +01:00
  • ad5fd5b60c Make prompt randomization optional. (#300) tjohnman 2023-03-19 19:36:19 +01:00
  • c98f6cd405 Respect the maximum number of tokens in interactive. (#298) tjohnman 2023-03-19 19:31:17 +01:00
  • 368d0c8a9e Respect the maximum number of tokens in interactive. (#298) tjohnman 2023-03-19 19:31:17 +01:00
  • d51eb6a70f Add --ignore-eos parameter (#181) slaren 2023-03-19 19:22:48 +01:00
  • 50fae10d03 Add --ignore-eos parameter (#181) slaren 2023-03-19 19:22:48 +01:00
  • d0eef77580 interactive mode: print '\n' in sigint_handler, this flush stdout thus ensure color reset. (#283) Qingyou Meng 2023-03-20 02:10:00 +08:00
  • 084e2f0ec0 interactive mode: print '\n' in sigint_handler, this flush stdout thus ensure color reset. (#283) Qingyou Meng 2023-03-20 02:10:00 +08:00
  • 30ea62e25d Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294) Erik Scholz 2023-03-19 18:57:00 +01:00
  • 0b366e7357 Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294) Erik Scholz 2023-03-19 18:57:00 +01:00
  • eed44b2875 Update hot topics to mention Alpaca support Georgi Gerganov 2023-03-19 19:51:55 +02:00