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

Commit graph

  • c8e13a78d0 Re-organize examples folder Andrei Betlen 2023-04-05 04:10:13 -0400
  • c16bda5fb9 Add performance tuning notebook Andrei Betlen 2023-04-05 04:09:19 -0400
  • cefc69ea43 Add runtime check to ensure embedding is enabled if trying to generate embeddings Andrei Betlen 2023-04-05 03:25:37 -0400
  • 5c50af7462 Remove workaround Andrei Betlen 2023-04-05 03:25:09 -0400
  • c3972b61ae Add basic tests. Closes #24 Andrei Betlen 2023-04-05 03:23:15 -0400
  • 51dbcf2693 Bugfix: wrong signature for quantize function Andrei Betlen 2023-04-04 22:36:59 -0400
  • 8279fb7d92 Bump version Andrei Betlen 2023-04-04 17:17:11 -0400
  • c137789143 Add verbose flag. Closes #19 Andrei Betlen 2023-04-04 13:09:24 -0400
  • 5075c16fcc Bugfix: n_batch should always be <= n_ctx Andrei Betlen 2023-04-04 13:08:21 -0400
  • c862e8bac5 Fix repeating instructions and an antiprompt bug Mug 2023-04-04 17:54:47 +0200
  • 248b0566fa Update README Andrei Betlen 2023-04-04 10:57:22 -0400
  • 9cde7973cc Fix stripping instruction prompt Mug 2023-04-04 16:20:27 +0200
  • da5a6a7089 Added instruction mode, fixed infinite generation, and various other fixes Mug 2023-04-04 16:18:26 +0200
  • 0b32bb3d43 Add instruction mode Mug 2023-04-04 11:48:48 +0200
  • ffe34cf64d Allow user to set llama config from env vars Andrei Betlen 2023-04-04 00:52:44 -0400
  • 05eb2087d8 Small fixes for examples Andrei Betlen 2023-04-03 20:33:07 -0400
  • caf3c0362b Add return type for default __call__ method Andrei Betlen 2023-04-03 20:26:08 -0400
  • 4aa349d777 Add docstring for create_chat_completion Andrei Betlen 2023-04-03 20:24:20 -0400
  • 4615f1e520 Add chat completion method to docs Andrei Betlen 2023-04-03 20:14:03 -0400
  • 5cf29d0231 Bump version Andrei Betlen 2023-04-03 20:13:46 -0400
  • 7fedf16531 Add support for chat completion Andrei Betlen 2023-04-03 20:12:44 -0400
  • 3dec778c90 Update to more sensible return signature Andrei Betlen 2023-04-03 20:12:14 -0400
  • f7ab8d55b2 Update context size defaults Close #11 Andrei Betlen 2023-04-03 20:11:13 -0400
  • c0a5c0171f Add embed back into documentation Andrei Betlen 2023-04-03 18:53:00 -0400
  • adf656d542 Bump version Andrei Betlen 2023-04-03 18:46:49 -0400
  • ae004eb69e Fix #16 Andrei Betlen 2023-04-03 18:46:19 -0400
  • f1615f05e6 Chat llama.cpp example implementation Mug 2023-04-03 22:54:46 +0200
  • 7d1977e8f0 Bump version Andrei Betlen 2023-04-03 14:49:36 -0400
  • 4530197629 Update llama.cpp Andrei Betlen 2023-04-03 14:49:07 -0400
  • 1d9a988644
         Merge pull request #10 from MillionthOdin16/patch-1 Andrei 2023-04-03 14:47:11 -0400
  • a0758f0077
         Update llama_cpp.py with PR requests MillionthOdin16 2023-04-03 13:06:50 -0400
  • a40476e299
         Update llama_cpp.py MillionthOdin16 2023-04-02 21:50:13 -0400
  • b9a4513363 Update README Andrei Betlen 2023-04-02 21:03:39 -0400
  • 7284adcaa8 Bump version Andrei Betlen 2023-04-02 13:36:07 -0400
  • 1ed8cd023d Update llama_cpp and add kv_cache api support Andrei Betlen 2023-04-02 13:33:49 -0400
  • 74061b209d Bump version Andrei Betlen 2023-04-02 03:59:47 -0400
  • 4f509b963e Bugfix: Stop sequences and missing max_tokens check Andrei Betlen 2023-04-02 03:59:19 -0400
  • 42dd11c2b4 Bump version Andrei Betlen 2023-04-02 00:10:46 -0400
  • 2bc184dc63 Add new methods to docs Andrei Betlen 2023-04-02 00:09:51 -0400
  • 353e18a781 Move workaround to new sample method Andrei Betlen 2023-04-02 00:06:34 -0400
  • a4a1bbeaa9 Update api to allow for easier interactive mode Andrei Betlen 2023-04-02 00:02:47 -0400
  • eef627c09c Fix example documentation Andrei Betlen 2023-04-01 17:39:35 -0400
  • a836639822 Bump version Andrei Betlen 2023-04-01 17:37:05 -0400
  • 1e4346307c Add documentation for generate method Andrei Betlen 2023-04-01 17:36:30 -0400
  • 33f1529c50 Bump version Andrei Betlen 2023-04-01 17:30:47 -0400
  • f14a31c936 Document generate method Andrei Betlen 2023-04-01 17:29:43 -0400
  • 67c70cc8eb Add static methods for beginning and end of sequence tokens. Andrei Betlen 2023-04-01 17:29:30 -0400
  • caff127836 Remove commented out code Andrei Betlen 2023-04-01 15:13:01 -0400
  • f28bf3f13d Bugfix: enable embeddings for fastapi server Andrei Betlen 2023-04-01 15:12:25 -0400
  • c25b7dfc86 Bump version Andrei Betlen 2023-04-01 13:06:05 -0400
  • ed6f2a049e Add streaming and embedding endpoints to fastapi example Andrei Betlen 2023-04-01 13:05:20 -0400
  • 0503e7f9b4 Update api Andrei Betlen 2023-04-01 13:04:12 -0400
  • 9f975ac44c Add development section Andrei Betlen 2023-04-01 13:03:56 -0400
  • 9fac0334b2 Update embedding example to new api Andrei Betlen 2023-04-01 13:02:51 -0400
  • 5e011145c5 Update low level api example Andrei Betlen 2023-04-01 13:02:10 -0400
  • 5f2e822b59 Rename inference example Andrei Betlen 2023-04-01 13:01:45 -0400
  • 318eae237e Update high-level api Andrei Betlen 2023-04-01 13:01:27 -0400
  • 3af274cbd4 Update llama.cpp Andrei Betlen 2023-04-01 13:00:09 -0400
  • 69e7d9f60e Add type definitions Andrei Betlen 2023-04-01 12:59:58 -0400
  • 49c8df369a Fix type signature of token_to_str Andrei Betlen 2023-03-31 03:25:12 -0400
  • 670d390001 Fix ctypes typing issue for Arrays Andrei Betlen 2023-03-31 03:20:15 -0400
  • 1545b22727 Fix array type signatures Andrei Betlen 2023-03-31 02:08:20 -0400
  • 4b9eb5c19e Add search to mkdocs Andrei Betlen 2023-03-31 00:01:53 -0400
  • f5e03805f7 Update llama.cpp Andrei Betlen 2023-03-31 00:00:43 -0400
  • c928e0afc8 Formatting Andrei Betlen 2023-03-31 00:00:27 -0400
  • 8d9560ed66 Add typing-extensions dependency Andrei Betlen 2023-03-30 06:43:31 -0400
  • a596362c44 Add minimum python version, typing-extensions dependency, and long description for PyPI Andrei Betlen 2023-03-30 06:42:54 -0400
  • 51a92b5146 Bump version Andrei Betlen 2023-03-28 21:10:49 -0400
  • 8908f4614c Update llama.cpp Andrei Betlen 2023-03-28 21:10:23 -0400
  • ea41474e04 Add new Llama methods to docs Andrei Betlen 2023-03-28 05:04:15 -0400
  • f11e9ae939 Bump version Andrei Betlen 2023-03-28 05:00:31 -0400
  • 70b8a1ef75 Add support to get embeddings from high-level api. Closes #4 Andrei Betlen 2023-03-28 04:59:54 -0400
  • 9ba5c3c3b7 Bump version Andrei Betlen 2023-03-28 04:04:35 -0400
  • 3dbb3fd3f6 Add support for stream parameter. Closes #1 Andrei Betlen 2023-03-28 04:03:57 -0400
  • 30fc0f3866 Extract generate method Andrei Betlen 2023-03-28 02:42:22 -0400
  • 1c823f6d0f Refactor Llama class and add tokenize / detokenize methods Closes #3 Andrei Betlen 2023-03-28 01:45:37 -0400
  • 6dbff7679c Add docs link Andrei Betlen 2023-03-27 18:30:12 -0400
  • c210635c9b Update llama.cpp Andrei Betlen 2023-03-27 01:35:51 -0400
  • 0ea84df91c Update llama.cpp Andrei Betlen 2023-03-26 14:00:37 -0400
  • 4250380c0a Bump version Andrei Betlen 2023-03-25 16:26:35 -0400
  • 8ae3beda9c Update Llama to add params Andrei Betlen 2023-03-25 16:26:23 -0400
  • 4525236214 Update llama.cpp Andrei Betlen 2023-03-25 16:26:03 -0400
  • b121b7c05b Update docstring Andrei Betlen 2023-03-25 12:33:18 -0400
  • 206efa39df Bump version Andrei Betlen 2023-03-25 12:12:39 -0400
  • fa92740a10 Update llama.cpp Andrei Betlen 2023-03-25 12:12:09 -0400
  • dfe8608096 Update examples Andrei Betlen 2023-03-24 19:10:31 -0400
  • 5533ed7aa8 Update docs Andrei Betlen 2023-03-24 19:02:36 -0400
  • cbf8a62b64 Add repo url Andrei Betlen 2023-03-24 18:59:02 -0400
  • df15caa877 Add mkdocs Andrei Betlen 2023-03-24 18:57:59 -0400
  • a61fd3b509 Add example based on stripped down version of main.cpp from llama.cpp Andrei Betlen 2023-03-24 18:57:25 -0400
  • da9b71cfe5 Bump version Andrei Betlen 2023-03-24 18:44:04 -0400
  • 4da5faa28b Bugfix: cross-platform method to find shared lib Andrei Betlen 2023-03-24 18:43:29 -0400
  • b93675608a Handle errors returned by llama.cpp Andrei Betlen 2023-03-24 15:47:17 -0400
  • bcde1f19b7 Bump version Andrei Betlen 2023-03-24 15:00:10 -0400
  • 7786edb0f9 Black formatting Andrei Betlen 2023-03-24 14:59:29 -0400
  • c784d83131 Update llama.cpp and re-organize low-level api Andrei Betlen 2023-03-24 14:58:42 -0400
  • b9c53b88a1 Use n_ctx provided from actual context not params Andrei Betlen 2023-03-24 14:58:10 -0400
  • 2cc499512c Black formatting Andrei Betlen 2023-03-24 14:35:41 -0400
  • d29b05bb67 Update example to match alpaca training prompt Andrei Betlen 2023-03-24 14:34:15 -0400
  • e24c581b5a Implement prompt batch processing as in main.cpp Andrei Betlen 2023-03-24 14:33:38 -0400