Commit Graph

  • 3490c2eb19 build : fix build info generation and cleanup Makefile (#3920) Jared Van Bortel 2023-11-30 17:23:08 -05:00
  • 15f5d96037 build : fix build info generation and cleanup Makefile (#3920) Jared Van Bortel 2023-11-30 17:23:08 -05:00
  • 53efe4ab1d llava : ShareGPT4V compatibility (vision encoder only loading) (#4172) John 2023-11-30 23:11:14 +01:00
  • 33c9892af5 llava : ShareGPT4V compatibility (vision encoder only loading) (#4172) John 2023-11-30 23:11:14 +01:00
  • 10ba0288a3 main : pass LOG_TEE callback to llama.cpp log (#4033) Andrew Godfrey 2023-11-30 13:56:19 -08:00
  • 8efa0f6ebe main : pass LOG_TEE callback to llama.cpp log (#4033) Andrew Godfrey 2023-11-30 13:56:19 -08:00
  • bc91cdbd87 readme : fix (#4135) vodkaslime 2023-12-01 05:49:21 +08:00
  • 524907aa76 readme : fix (#4135) vodkaslime 2023-12-01 05:49:21 +08:00
  • d50cb16dbe docker : add finetune option (#4211) Juraj Bednar 2023-11-30 22:46:01 +01:00
  • 3bd2c7ce1b docker : add finetune option (#4211) Juraj Bednar 2023-11-30 22:46:01 +01:00
  • 27645bac96 batched.swift : update README.md (#4214) Miwa / Ensan 2023-12-01 06:45:17 +09:00
  • bde629bb53 batched.swift : update README.md (#4214) Miwa / Ensan 2023-12-01 06:45:17 +09:00
  • c7df772921 cmake : fix the metal file foder path (#4217) Li Tan 2023-11-30 13:44:11 -08:00
  • f7f9e06212 cmake : fix the metal file foder path (#4217) Li Tan 2023-11-30 13:44:11 -08:00
  • 8f1e6fbde7 readme : fix typo (#4253) Dawid Wysocki 2023-11-30 22:43:32 +01:00
  • 74daabae69 readme : fix typo (#4253) Dawid Wysocki 2023-11-30 22:43:32 +01:00
  • 40ba0ff316 llama : fix alignment of general.name in print meta (#4254) Daniel Bevenius 2023-11-30 22:43:08 +01:00
  • b18c66ca6e llama : fix alignment of general.name in print meta (#4254) Daniel Bevenius 2023-11-30 22:43:08 +01:00
  • d9a95928b3 convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#4258) slaren 2023-11-30 22:42:23 +01:00
  • f4d973cecb convert.py : fix llama/llama2 conversion due to vocab_size=-1 (#4258) slaren 2023-11-30 22:42:23 +01:00
  • e8679910c5 llama : fix typical sampling (#4261) tarcey 2023-11-30 22:40:23 +01:00
  • 954e22858c llama : fix typical sampling (#4261) tarcey 2023-11-30 22:40:23 +01:00
  • 36a0f98394 py : fix oai proxy (#3972) rhjdvsgsgks 2023-11-30 20:50:40 +00:00
  • e2bd725f4b py : fix oai proxy (#3972) rhjdvsgsgks 2023-11-30 20:50:40 +00:00
  • 65125b5b15 examples : add readme files Georgi Gerganov 2023-11-29 11:00:17 +02:00
  • 1f5cd83275 examples : add readme files Georgi Gerganov 2023-11-29 11:00:17 +02:00
  • d119cde4a5 readme : add FreeChat (#4248) Peter Sugihara 2023-11-28 23:16:34 -08:00
  • 4fea3420ee readme : add FreeChat (#4248) Peter Sugihara 2023-11-28 23:16:34 -08:00
  • a52ca740f0 ggml : restore abort() in GGML_ASSERT (#4242) Jared Van Bortel 2023-11-28 04:51:11 -05:00
  • 64e64aa255 ggml : restore abort() in GGML_ASSERT (#4242) Jared Van Bortel 2023-11-28 04:51:11 -05:00
  • 0a090ef12c ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240) Georgi Gerganov 2023-11-28 10:32:03 +02:00
  • 8406b0924b ggml : re-enable BLAS for CPU when src0 != F32 + remove redundant full offload checks in llama.cpp (#4240) Georgi Gerganov 2023-11-28 10:32:03 +02:00
  • b854430d8d cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970) bandoti 2023-11-27 15:25:42 -04:00
  • b38a16dfcf cmake : fix issue with version info not getting baked into LlamaConfig.cmake (#3970) bandoti 2023-11-27 15:25:42 -04:00
  • 2cf38d14b2 readme : add Amica to UI list (#4230) Kasumi 2023-11-28 01:39:42 +08:00
  • 0dab8cd7cc readme : add Amica to UI list (#4230) Kasumi 2023-11-28 01:39:42 +08:00
  • a6a660c556 examples : iOS example with swift ui (#4159) Bailey Chittle 2023-11-27 09:56:52 -05:00
  • bb03290c17 examples : iOS example with swift ui (#4159) Bailey Chittle 2023-11-27 09:56:52 -05:00
  • cbf9b1ab9f ggml : fix -Warray-bounds warning with gcc (#4231) Jared Van Bortel 2023-11-26 22:58:43 -05:00
  • f3b269813f ggml : fix -Warray-bounds warning with gcc (#4231) Jared Van Bortel 2023-11-26 22:58:43 -05:00
  • 03d295f72b lookahead : support -n -1 infinite generation Georgi Gerganov 2023-11-26 21:51:46 +02:00
  • 3e73d31d9c lookahead : support -n -1 infinite generation Georgi Gerganov 2023-11-26 21:51:46 +02:00
  • 6f7d280455 readme : update hot topics Georgi Gerganov 2023-11-26 20:42:51 +02:00
  • 9656026b53 readme : update hot topics Georgi Gerganov 2023-11-26 20:42:51 +02:00
  • 538b538dec lookahead : add example for lookahead decoding (#4207) Georgi Gerganov 2023-11-26 20:33:07 +02:00
  • 922754a8d6 lookahead : add example for lookahead decoding (#4207) Georgi Gerganov 2023-11-26 20:33:07 +02:00
  • 88a3cb0018 metal : fix yarn (#4220) Xiao-Yong Jin 2023-11-26 02:30:02 -06:00
  • 22da05536f metal : fix yarn (#4220) Xiao-Yong Jin 2023-11-26 02:30:02 -06:00
  • a733692578 scripts : Use mmap in torch load (#4202) Galunid 2023-11-25 22:45:02 +01:00
  • 1ddb52ec38 scripts : Use mmap in torch load (#4202) Galunid 2023-11-25 22:45:02 +01:00
  • 80f0235729 llama : grammar reserve space in decode_utf8 (#4210) Marcus Dunn 2023-11-25 08:58:23 -08:00
  • f837c3a992 llama : grammar reserve space in decode_utf8 (#4210) Marcus Dunn 2023-11-25 08:58:23 -08:00
  • 37ec1b749b Update docs for yarn_ext_factor <0.0 as unspecified instead of NaN (#4189) crasm 2023-11-25 10:47:07 -05:00
  • 3014b5415d Update docs for yarn_ext_factor <0.0 as unspecified instead of NaN (#4189) crasm 2023-11-25 10:47:07 -05:00
  • e5d642885c readme : update hot topics Georgi Gerganov 2023-11-25 12:02:13 +02:00
  • 04814e718e readme : update hot topics Georgi Gerganov 2023-11-25 12:02:13 +02:00
  • 029ba0645a server : OAI API compatibility (#4198) Georgi Gerganov 2023-11-25 11:29:06 +02:00
  • af19d35734 server : OAI API compatibility (#4198) Georgi Gerganov 2023-11-25 11:29:06 +02:00
  • 0294f47e0f llama : set metal log callback correctly (#4204) slaren 2023-11-24 18:10:01 +01:00
  • e9c13ff781 llama : set metal log callback correctly (#4204) slaren 2023-11-24 18:10:01 +01:00
  • 69d39de984 ggml-cuda : support stablelm rope (#4156) slaren 2023-11-24 18:04:31 +01:00
  • 8a052c131e ggml-cuda : support stablelm rope (#4156) slaren 2023-11-24 18:04:31 +01:00
  • 56cc14d002 convert : fix tensors using grad in some models (#4173) Galunid 2023-11-24 15:02:49 +01:00
  • 189d68446e convert : fix tensors using grad in some models (#4173) Galunid 2023-11-24 15:02:49 +01:00
  • 1c9603e5de main.swift : fix eos checking (#4197) eastriver 2023-11-24 18:25:10 +09:00
  • 2568a4bf54 main.swift : fix eos checking (#4197) eastriver 2023-11-24 18:25:10 +09:00
  • 92eb4cdab4 readme : use PATH for Windows ROCm (#4195) Aaryaman Vasishta 2023-11-24 16:52:39 +09:00
  • b35f3d0def readme : use PATH for Windows ROCm (#4195) Aaryaman Vasishta 2023-11-24 16:52:39 +09:00
  • 519c2d7f6d Fix incorrect format strings and uninitialized variables. (#4133) Haohui Mai 2023-11-23 13:56:53 -08:00
  • 55978ce09b Fix incorrect format strings and uninitialized variables. (#4133) Haohui Mai 2023-11-23 13:56:53 -08:00
  • b2ea5096c7 llama : KV cache view API + better KV cache management (#4170) Georgi Gerganov 2023-11-23 19:07:56 +02:00
  • 6b0a7420d0 llama : KV cache view API + better KV cache management (#4170) Georgi Gerganov 2023-11-23 19:07:56 +02:00
  • a8e65a6b4c readme : update hot topics Georgi Gerganov 2023-11-23 13:51:22 +02:00
  • d103d935c0 readme : update hot topics Georgi Gerganov 2023-11-23 13:51:22 +02:00
  • 3634898fc9 examples : fix typo in parallel example doc comment (#4181) Daniel Bevenius 2023-11-23 12:34:20 +01:00
  • 9d5949f04b examples : fix typo in parallel example doc comment (#4181) Daniel Bevenius 2023-11-23 12:34:20 +01:00
  • d490717332 docs : add llama-star arch idea Georgi Gerganov 2023-11-23 11:35:04 +02:00
  • ff8238f71d docs : add llama-star arch idea Georgi Gerganov 2023-11-23 11:35:04 +02:00
  • 2131fd00f6 stablelm : simplify + speedup generation (#4153) Galunid 2023-11-21 16:22:30 +01:00
  • 8e672efe63 stablelm : simplify + speedup generation (#4153) Galunid 2023-11-21 16:22:30 +01:00
  • 36b4b555a1 finetune - update readme to mention llama support only (#4148) Galunid 2023-11-20 19:30:00 +01:00
  • 0b871f1a04 finetune - update readme to mention llama support only (#4148) Galunid 2023-11-20 19:30:00 +01:00
  • 94da394760 readme : update ROCm Windows instructions (#4122) Aaryaman Vasishta 2023-11-21 00:02:46 +09:00
  • dfc7cd48b1 readme : update ROCm Windows instructions (#4122) Aaryaman Vasishta 2023-11-21 00:02:46 +09:00
  • 1e327356e7 main : Add ChatML functionality to main example (#4046) Seb C 2023-11-21 00:26:59 +10:30
  • 881800d1f0 main : Add ChatML functionality to main example (#4046) Seb C 2023-11-21 00:26:59 +10:30
  • e9076069eb ci : add flake8 to github actions (python linting) (#4129) Galunid 2023-11-20 11:35:47 +01:00
  • f23c0359a3 ci : add flake8 to github actions (python linting) (#4129) Galunid 2023-11-20 11:35:47 +01:00
  • 6eb092e1fd speculative : fix prompt tokenization in speculative example (#4025) Branden Butler 2023-11-20 03:50:04 -06:00
  • 40a34fe8d0 speculative : fix prompt tokenization in speculative example (#4025) Branden Butler 2023-11-20 03:50:04 -06:00
  • e0a3aa1105 Revert "finetune : add --n-gpu-layers flag info to --help (#4128)" Georgi Gerganov 2023-11-19 19:16:07 +02:00
  • dae06c06e5 Revert "finetune : add --n-gpu-layers flag info to --help (#4128)" Georgi Gerganov 2023-11-19 19:16:07 +02:00
  • 4acb5f6aeb finetune : add --n-gpu-layers flag info to --help (#4128) Clark Saben 2023-11-19 11:56:38 -05:00
  • 05e8301e45 finetune : add --n-gpu-layers flag info to --help (#4128) Clark Saben 2023-11-19 11:56:38 -05:00
  • dd8b85d642 server : relay error messages (#4131) SoftwareRenderer 2023-11-19 11:54:10 -05:00
  • 936c79b227 server : relay error messages (#4131) SoftwareRenderer 2023-11-19 11:54:10 -05:00
  • 53c8eda354 common : comma should be semicolon (#4137) kchro3 2023-11-19 08:52:57 -08:00
  • 262005ad9d common : comma should be semicolon (#4137) kchro3 2023-11-19 08:52:57 -08:00
  • 5d1ea84281 gitignore : tokenize Georgi Gerganov 2023-11-19 18:50:49 +02:00
  • 35985acffa gitignore : tokenize Georgi Gerganov 2023-11-19 18:50:49 +02:00