abetlen/llama-cpp-python
1
0
Fork 0
mirror of https://github.com/abetlen/llama-cpp-python.git synced 2026-03-28 03:41:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 7dbbfdecad fix: submodule kompute is not included in sdist. Closes #1165 Andrei Betlen 2024-02-13 23:53:56 -05:00
  • 345215a76c fix: more chatml-function-calling fixes Andrei Betlen 2024-02-13 23:02:50 -05:00
  • b1637c2319 Bump version v0.2.42 Andrei Betlen 2024-02-13 12:35:04 -05:00
  • d6be5333e1 fix: sample idx off-by-one error for logit_processors (#1179) Andrew Lapp 2024-02-13 17:26:07 +00:00
  • f7cdf78788 Update llama.cpp Andrei Betlen 2024-02-13 12:24:00 -05:00
  • 68fb71b6a2 fix: missing generation_prompt in chatml-function-calling Andrei Betlen 2024-02-13 03:24:41 -05:00
  • 4b0e3320bd fix: minor formatting bugs for chatml-function-calling Andrei Betlen 2024-02-13 03:11:35 -05:00
  • 6fe8b427e1 Bump version v0.2.41 Andrei Betlen 2024-02-13 02:46:52 -05:00
  • d1822fed6b fix: Don't change order of json schema object properties unless prop_order is passed, Closes #1180 Andrei Betlen 2024-02-13 02:44:00 -05:00
  • 5efc45bdfd Update llama.cpp Andrei Betlen 2024-02-13 02:43:07 -05:00
  • 4348a6cdf0 docs: Fix typo Andrei Betlen 2024-02-13 02:04:54 -05:00
  • d605875772 Bump version v0.2.40 Andrei Betlen 2024-02-12 16:28:30 -05:00
  • b82b0e1014 docs: Temporarily revert function calling docs Andrei Betlen 2024-02-12 16:27:43 -05:00
  • cb791716b4 fix: Always set logits_all = True when using speculative decoding Andrei Betlen 2024-02-12 16:19:05 -05:00
  • 153a0049d9 feat: Generic chatml Function Calling (#957) Andrei 2024-02-12 15:56:07 -05:00
  • 69413ce08e Update llama.cpp Andrei Betlen 2024-02-11 19:00:17 -05:00
  • 9368670639 Update llama.cpp Andrei Betlen 2024-02-11 14:02:46 -05:00
  • a05d90446f fix: Circular dependancy preventing early Llama object free (#1176) Connor 2024-02-11 10:57:57 -08:00
  • 918ff27e50 docs: Set the correct command for compiling with syscl support (#1172) Akarshan Biswas 2024-02-12 00:25:15 +05:30
  • 19b55ad3e5 feat: use gpu backend for clip if available (#1175) Douglas Hanley 2024-02-11 12:53:59 -06:00
  • 63b0c37836 Update llama.cpp Andrei Betlen 2024-02-09 13:36:58 -05:00
  • 4abb8c9386 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2024-02-09 13:32:31 -05:00
  • e16f06e6eb fix: revert _create_completions. Andrei Betlen 2024-02-09 02:02:13 -05:00
  • dfc1b17341 Update llama.cpp Andrei Betlen 2024-02-08 23:38:12 -05:00
  • 5b4ad6c80b Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-02-08 23:34:45 -05:00
  • 85d3374b4d fix: broken import Andrei Betlen 2024-02-08 01:13:28 -05:00
  • b5fca911b5 feat: Move tokenizer to own module Andrei Betlen 2024-02-08 01:08:18 -05:00
  • 2ef7ba3aed misc: rename grammar test Andrei Betlen 2024-02-08 01:07:44 -05:00
  • 901827013b feat: Integrate functionary v1.4 and v2 models + add custom tokenizer support to Llama class (#1078) Jeffrey Fong 2024-02-08 09:07:03 +08:00
  • ce12775490 Update llama.cpp Andrei Betlen 2024-02-06 18:50:56 -05:00
  • 34f31040f6 Bump version v0.2.39 Andrei Betlen 2024-02-06 12:47:59 -05:00
  • 5e3e67af47 Update llama.cpp Andrei Betlen 2024-02-06 12:44:07 -05:00
  • 310fbf4e49 Update llama.cpp Andrei Betlen 2024-02-05 22:07:14 -05:00
  • 59760c85ed fix: Use llama_log_callback to avoid suppress_stdout_stderr Andrei Betlen 2024-02-05 21:52:12 -05:00
  • 3553b14670 Update llama.cpp Andrei Betlen 2024-02-05 13:26:50 -05:00
  • 7467f129e5 Revert "Fix: fileno error google colab (#729) (#1156)" (#1157) Andrei 2024-02-02 12:18:55 -05:00
  • bebfba0f08 Fix: fileno error google colab (#729) (#1156) Dulsara 2024-02-02 22:35:46 +05:30
  • 8a5911bd5d Update llama.cpp Andrei Betlen 2024-02-02 09:41:27 -05:00
  • de526d0214 Update llama.cpp Andrei Betlen 2024-02-01 12:35:31 -05:00
  • 3322eadbf3 Bump version v0.2.38 Andrei Betlen 2024-01-31 15:10:18 -05:00
  • a8cb34eacd Update llama.cpp Andrei Betlen 2024-01-31 15:05:51 -05:00
  • 7a9f63959d Test dummy image tags in chat templates Andrei Betlen 2024-01-31 14:13:05 -05:00
  • fb762a6041 Add speculative decoding (#1120) Andrei 2024-01-31 14:08:14 -05:00
  • 71e3e4c435 Update llama.cpp Andrei Betlen 2024-01-31 10:41:42 -05:00
  • 2b37d8e438 fix: Run server command. Closes #1143 Andrei Betlen 2024-01-31 10:37:19 -05:00
  • 078cca0361 fix: Pass raise_exception and add_generation_prompt to jinja2 chat template Andrei Betlen 2024-01-31 08:42:21 -05:00
  • 411494706a Update llama.cpp Andrei Betlen 2024-01-31 08:35:21 -05:00
  • bf9e824922 Bump version v0.2.37 Andrei Betlen 2024-01-30 12:27:27 -05:00
  • 247a16de66 docs: Update README Andrei Betlen 2024-01-30 12:23:07 -05:00
  • 13b7ced7da Update llama.cpp Andrei Betlen 2024-01-30 12:21:41 -05:00
  • 011cd84ded Update llama.cpp Andrei Betlen 2024-01-30 09:48:09 -05:00
  • da003d8768 Automatically set chat format from gguf (#1110) Andrei 2024-01-29 14:22:23 -05:00
  • 059f6b3ac8 docs: fix typos Andrei Betlen 2024-01-29 11:02:25 -05:00
  • 843e77e3e2 docs: Add Vulkan build instructions Andrei Betlen 2024-01-29 11:01:26 -05:00
  • 464af5b39f Bump version v0.2.36 Andrei Betlen 2024-01-29 10:46:04 -05:00
  • 9f7852acfa misc: Add vulkan target Andrei Betlen 2024-01-29 10:39:23 -05:00
  • 85f8c4c06e Update llama.cpp Andrei Betlen 2024-01-29 10:39:08 -05:00
  • 9ae5819ee4 Add chat format test. Andrei Betlen 2024-01-29 00:59:01 -05:00
  • ce38dbdf07 Add mistral instruct chat format as "mistral-instruct" (#799) Rafaelblsilva 2024-01-29 02:34:42 -03:00
  • 52c4a84faf Bump version v0.2.35 Andrei Betlen 2024-01-28 19:35:37 -05:00
  • 31e0288a41 Update llama.cpp Andrei Betlen 2024-01-28 19:34:27 -05:00
  • ccf4908bfd Update llama.cpp Andrei Betlen 2024-01-28 12:55:32 -05:00
  • 8c59210062 docs: Fix typo Andrei Betlen 2024-01-27 19:37:59 -05:00
  • 399fa1e03b docs: Add JSON and JSON schema mode examples to README Andrei Betlen 2024-01-27 19:36:33 -05:00
  • c1d0fff8a9 Bump version v0.2.34 Andrei Betlen 2024-01-27 18:36:56 -05:00
  • d8f6914f45 Add json schema mode (#1122) Andrei 2024-01-27 16:52:18 -05:00
  • c6d3bd62e8 Update llama.cpp Andrei Betlen 2024-01-27 16:22:46 -05:00
  • 35918873b4 Update llama.cpp Andrei Betlen 2024-01-26 11:45:48 -05:00
  • f5cc6b3053 Bump version v0.2.33 Andrei Betlen 2024-01-25 11:28:16 -05:00
  • cde7514c3d feat(server): include llama-cpp-python version in openapi spec Andrei Betlen 2024-01-25 11:23:18 -05:00
  • 2588f34a22 Update llama.cpp Andrei Betlen 2024-01-25 11:22:42 -05:00
  • dc5a436224 Update llama.cpp Andrei Betlen 2024-01-25 11:19:34 -05:00
  • d6fb16e055 docs: Update README Andrei Betlen 2024-01-25 10:51:48 -05:00
  • 5b258bf840 docs: Update README with more param common examples Andrei Betlen 2024-01-24 10:51:15 -05:00
  • c343baaba8 Update llama.cpp Andrei Betlen 2024-01-24 10:40:50 -05:00
  • c970d41a85 fix: llama_log_set should be able to accept null pointer Andrei Betlen 2024-01-24 10:38:30 -05:00
  • 9677a1f2c8 fix: Check order Andrei Betlen 2024-01-23 22:28:03 -05:00
  • 4d6b2f7b91 fix: format Andrei Betlen 2024-01-23 22:08:27 -05:00
  • fe5d6ea648 fix: GGUF metadata KV overrides, re #1011 (#1116) Phil H 2024-01-24 03:00:38 +00:00
  • 7e63928bc9 Update llama.cpp Andrei Betlen 2024-01-23 18:42:39 -05:00
  • fcdf337d84 Update llama.cpp Andrei Betlen 2024-01-22 11:25:11 -05:00
  • 5b982d0f8c fix: use both eos and bos tokens as stop sequences for hf-tokenizer-config chat format. Andrei Betlen 2024-01-22 08:32:48 -05:00
  • 2ce0b8aa2c Bump version v0.2.32 Andrei Betlen 2024-01-21 20:30:24 -05:00
  • d3f5528ca8 fix: from_json_schema oneof/anyof bug. Closes #1097 Andrei Betlen 2024-01-21 19:06:53 -05:00
  • 8eefdbca03 Update llama.cpp Andrei Betlen 2024-01-21 19:01:27 -05:00
  • 88fbccaaa3 docs: Add macosx wrong arch fix to README Andrei Betlen 2024-01-21 18:38:44 -05:00
  • 24f39454e9 fix: pass chat handler not chat formatter for huggingface autotokenizer and tokenizer_config formats. Andrei Betlen 2024-01-21 18:38:04 -05:00
  • 7f3209b1eb feat: Add add_generation_prompt option for jinja2chatformatter. Andrei Betlen 2024-01-21 18:37:24 -05:00
  • ac2e96d4b4 Update llama.cpp Andrei Betlen 2024-01-19 15:33:43 -05:00
  • be09318c26 feat: Add Jinja2ChatFormatter Andrei Betlen 2024-01-19 15:04:42 -05:00
  • 5a34c57e54 feat: Expose gguf model metadata in metadata property Andrei Betlen 2024-01-19 10:46:03 -05:00
  • 833a7f1a86 Bump version v0.2.31 Andrei Betlen 2024-01-19 09:03:35 -05:00
  • e21c3c7a91 Update makefile Andrei Betlen 2024-01-19 08:47:56 -05:00
  • 0f54948482 Update llama.cpp Andrei Betlen 2024-01-19 08:41:52 -05:00
  • 3babe3512c Fix mirostat sampling Andrei Betlen 2024-01-19 08:31:59 -05:00
  • 141293a75b Fix python3.8 support Andrei Betlen 2024-01-19 08:17:49 -05:00
  • 656f3d8968 Bump version v0.2.30 Andrei Betlen 2024-01-18 21:30:36 -05:00
  • 03ed547bfd Remove templates doc Andrei Betlen 2024-01-18 21:23:26 -05:00
  • 3ca86ab390 Update llama.cpp Andrei Betlen 2024-01-18 21:22:45 -05:00
  • be23404ed4 Cleanup pyproject Andrei Betlen 2024-01-18 21:22:19 -05:00