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

Commit graph

  • 32efed7b07 docs: Update README Andrei Betlen 2024-02-22 03:25:11 -0500
  • d80c5cf29d docs: fix indentation for mkdocs-material Andrei Betlen 2024-02-22 02:30:24 -0500
  • aefcb8f71a misc: additional type annotations for low level api Andrei Betlen 2024-02-22 02:00:09 -0500
  • 3921e10770 feat: support minItems/maxItems in JSON grammar converter (by @nopperl) Andrei Betlen 2024-02-22 00:17:06 -0500
  • e6d6260a91 fix: Update from_pretrained defaults to match hf_hub_download Andrei Betlen 2024-02-22 00:10:23 -0500
  • dd22010e85 fix: Raise exceptions when llama model or context fails to load Andrei Betlen 2024-02-22 00:09:45 -0500
  • 3632241e98 chore: Bump version Andrei Betlen 2024-02-21 23:09:13 -0500
  • 0653e15c20 feat: Update llama.cpp Andrei Betlen 2024-02-21 23:04:52 -0500
  • 7981e9ce1e chore: Bump version Andrei Betlen 2024-02-21 16:30:59 -0500
  • 7f3962e11c feat: Update llama.cpp Andrei Betlen 2024-02-21 16:27:56 -0500
  • 14191e9036 docs: Add create_chat_completion_openai_v1 to api reference Andrei Betlen 2024-02-21 16:26:49 -0500
  • fe5626cd40 misc: add .local pattern to gitignore Andrei Betlen 2024-02-21 16:26:30 -0500
  • 7f51b6071f
         feat(low-level-api): Improve API static type-safety and performance (#1205) Andrei 2024-02-21 16:25:38 -0500
  • 0f8aa4ab5c
         feat: Pull models directly from huggingface (#1206) Andrei 2024-02-21 16:25:10 -0500
  • e42f62c247 chore: Bump version Andrei Betlen 2024-02-21 11:09:40 -0500
  • 4edde21b3d feat: Update llama.cpp Andrei Betlen 2024-02-21 11:05:58 -0500
  • f57b01ac9b ci: add debug build to dev makefile Andrei Betlen 2024-02-21 11:04:30 -0500
  • 04fe33b999 feat: Update llama.cpp Andrei Betlen 2024-02-20 02:59:02 -0500
  • d122bd7858 feat: Update llama.cpp Andrei Betlen 2024-02-19 22:10:16 -0500
  • 2264fbf750
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-02-19 18:51:06 +0530
  • 6225f027e5 feat: Update llama.cpp Andrei Betlen 2024-02-19 04:11:34 -0500
  • 748c0ce057 feat: Update llama.cpp Andrei Betlen 2024-02-18 21:30:36 -0500
  • 53f6f5f415 fix: self.numa missing Andrei Betlen 2024-02-17 01:02:33 -0500
  • fdce078cb9 feat: Update llama.cpp Andrei Betlen 2024-02-17 00:37:51 -0500
  • c2a234a086 docs: Add embeddings section Andrei Betlen 2024-02-15 23:15:50 -0500
  • f736827b9b chore: Bump version Andrei Betlen 2024-02-15 23:10:50 -0500
  • 0ce66bc080 fix: create_embedding broken response for input type str Andrei Betlen 2024-02-15 16:09:48 -0500
  • ea1f88dd29
         fix: Use '\n' seperator for EventSourceResponse (#1188) khimaros 2024-02-15 20:20:13 +0000
  • a5cfeb7763 feat: Update llama.cpp Andrei Betlen 2024-02-15 15:17:30 -0500
  • 7bb91f025f
         fix: Incorporate embedding pooling layer fixes (#1194) Douglas Hanley 2024-02-15 14:16:30 -0600
  • 21ac214a38
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-02-14 17:50:11 +0530
  • ae71ad1a14 Bump version Andrei Betlen 2024-02-14 04:31:42 -0500
  • f300d4310a Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-02-14 04:27:33 -0500
  • c336f78269 Update llama.cpp Andrei Betlen 2024-02-14 04:27:30 -0500
  • d7a67917ba
         feat: Support batch embeddings (#1186) Douglas Hanley 2024-02-14 03:26:09 -0600
  • 36b843228f misc: fix makefile build commands Andrei Betlen 2024-02-14 03:47:40 -0500
  • 7b9960d1cb Update llama.cpp Andrei Betlen 2024-02-14 03:47:21 -0500
  • 6943bab6d8 fix: destructor exception where internal classes are missing some uninitialized attributes Andrei Betlen 2024-02-14 03:38:41 -0500
  • 07a783779a fix: Update openbuddy prompt format. Closes #1155 Andrei Betlen 2024-02-13 23:57:10 -0500
  • 7a79e5ac49 Update llama.cpp Andrei Betlen 2024-02-13 23:54:05 -0500
  • 7dbbfdecad fix: submodule kompute is not included in sdist. Closes #1165 Andrei Betlen 2024-02-13 23:53:56 -0500
  • 345215a76c fix: more chatml-function-calling fixes Andrei Betlen 2024-02-13 23:02:50 -0500
  • b1637c2319 Bump version Andrei Betlen 2024-02-13 12:35:04 -0500
  • d6be5333e1
         fix: sample idx off-by-one error for logit_processors (#1179) Andrew Lapp 2024-02-13 17:26:07 +0000
  • f7cdf78788 Update llama.cpp Andrei Betlen 2024-02-13 12:24:00 -0500
  • 68fb71b6a2 fix: missing generation_prompt in chatml-function-calling Andrei Betlen 2024-02-13 03:24:41 -0500
  • 4b0e3320bd fix: minor formatting bugs for chatml-function-calling Andrei Betlen 2024-02-13 03:11:35 -0500
  • 6fe8b427e1 Bump version Andrei Betlen 2024-02-13 02:46:52 -0500
  • 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 -0500
  • 5efc45bdfd Update llama.cpp Andrei Betlen 2024-02-13 02:43:07 -0500
  • 4348a6cdf0 docs: Fix typo Andrei Betlen 2024-02-13 02:04:54 -0500
  • d605875772 Bump version Andrei Betlen 2024-02-12 16:28:30 -0500
  • b82b0e1014 docs: Temporarily revert function calling docs Andrei Betlen 2024-02-12 16:27:43 -0500
  • cb791716b4 fix: Always set logits_all = True when using speculative decoding Andrei Betlen 2024-02-12 16:19:05 -0500
  • 153a0049d9
         feat: Generic chatml Function Calling (#957) Andrei 2024-02-12 15:56:07 -0500
  • 69413ce08e Update llama.cpp Andrei Betlen 2024-02-11 19:00:17 -0500
  • 9368670639 Update llama.cpp Andrei Betlen 2024-02-11 14:02:46 -0500
  • a05d90446f
         fix: Circular dependancy preventing early Llama object free (#1176) Connor 2024-02-11 10:57:57 -0800
  • 918ff27e50
         docs: Set the correct command for compiling with syscl support (#1172) Akarshan Biswas 2024-02-12 00:25:15 +0530
  • 19b55ad3e5
         feat: use gpu backend for clip if available (#1175) Douglas Hanley 2024-02-11 12:53:59 -0600
  • 63b0c37836 Update llama.cpp Andrei Betlen 2024-02-09 13:36:58 -0500
  • 4abb8c9386 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2024-02-09 13:32:31 -0500
  • e16f06e6eb fix: revert _create_completions. Andrei Betlen 2024-02-09 02:02:13 -0500
  • dfc1b17341 Update llama.cpp Andrei Betlen 2024-02-08 23:38:12 -0500
  • 5b4ad6c80b Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-02-08 23:34:45 -0500
  • 85d3374b4d fix: broken import Andrei Betlen 2024-02-08 01:13:28 -0500
  • b5fca911b5 feat: Move tokenizer to own module Andrei Betlen 2024-02-08 01:08:18 -0500
  • 2ef7ba3aed misc: rename grammar test Andrei Betlen 2024-02-08 01:07:44 -0500
  • 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 +0800
  • ce12775490 Update llama.cpp Andrei Betlen 2024-02-06 18:50:56 -0500
  • 34f31040f6 Bump version Andrei Betlen 2024-02-06 12:47:59 -0500
  • 5e3e67af47 Update llama.cpp Andrei Betlen 2024-02-06 12:44:07 -0500
  • b342398804
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-02-06 16:26:03 +0530
  • 310fbf4e49 Update llama.cpp Andrei Betlen 2024-02-05 22:07:14 -0500
  • 59760c85ed fix: Use llama_log_callback to avoid suppress_stdout_stderr Andrei Betlen 2024-02-05 21:52:12 -0500
  • 3553b14670 Update llama.cpp Andrei Betlen 2024-02-05 13:26:50 -0500
  • 7467f129e5
         Revert "Fix: fileno error google colab (#729) (#1156)" (#1157) Andrei 2024-02-02 12:18:55 -0500
  • bebfba0f08
         Fix: fileno error google colab (#729) (#1156) Dulsara 2024-02-02 22:35:46 +0530
  • 8a5911bd5d Update llama.cpp Andrei Betlen 2024-02-02 09:41:27 -0500
  • de526d0214 Update llama.cpp Andrei Betlen 2024-02-01 12:35:31 -0500
  • 3322eadbf3 Bump version Andrei Betlen 2024-01-31 15:10:18 -0500
  • a8cb34eacd Update llama.cpp Andrei Betlen 2024-01-31 15:05:51 -0500
  • fb762a6041
         Add speculative decoding (#1120) Andrei 2024-01-31 14:08:14 -0500
  • cd66f3cfb4
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-01-31 21:27:17 +0530
  • 71e3e4c435 Update llama.cpp Andrei Betlen 2024-01-31 10:41:42 -0500
  • 2b37d8e438 fix: Run server command. Closes #1143 Andrei Betlen 2024-01-31 10:37:19 -0500
  • 078cca0361 fix: Pass raise_exception and add_generation_prompt to jinja2 chat template Andrei Betlen 2024-01-31 08:42:21 -0500
  • 411494706a Update llama.cpp Andrei Betlen 2024-01-31 08:35:21 -0500
  • bf9e824922 Bump version Andrei Betlen 2024-01-30 12:27:27 -0500
  • 247a16de66 docs: Update README Andrei Betlen 2024-01-30 12:23:07 -0500
  • 13b7ced7da Update llama.cpp Andrei Betlen 2024-01-30 12:21:41 -0500
  • 011cd84ded Update llama.cpp Andrei Betlen 2024-01-30 09:48:09 -0500
  • da003d8768
         Automatically set chat format from gguf (#1110) Andrei 2024-01-29 14:22:23 -0500
  • 059f6b3ac8 docs: fix typos Andrei Betlen 2024-01-29 11:02:25 -0500
  • 843e77e3e2 docs: Add Vulkan build instructions Andrei Betlen 2024-01-29 11:01:26 -0500
  • 464af5b39f Bump version Andrei Betlen 2024-01-29 10:46:04 -0500
  • 9f7852acfa misc: Add vulkan target Andrei Betlen 2024-01-29 10:39:23 -0500
  • 85f8c4c06e Update llama.cpp Andrei Betlen 2024-01-29 10:39:08 -0500
  • 9ae5819ee4 Add chat format test. Andrei Betlen 2024-01-29 00:59:01 -0500
  • ce38dbdf07
         Add mistral instruct chat format as "mistral-instruct" (#799) Rafaelblsilva 2024-01-29 02:34:42 -0300