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

Commit graph

  • aa9f1ae011
         feat: Add logprobs support to chat completions (#1311) windspirit95 2024-04-01 02:30:13 +0900
  • 1e60dba082 feat: Update llama.cpp Andrei Betlen 2024-03-29 13:34:23 -0400
  • dcbe57fcf8 feat: Update llama.cpp Andrei Betlen 2024-03-29 12:45:27 -0400
  • 125b2358c9 feat: Update llama.cpp Andrei Betlen 2024-03-28 12:06:46 -0400
  • 901fe02461 feat: Update llama.cpp Andrei Betlen 2024-03-26 22:58:53 -0400
  • b64fa4e2c0 feat: Update llama.cpp Andrei Betlen 2024-03-25 23:09:07 -0400
  • a93b9149f8 feat: Update llama.cpp Andrei Betlen 2024-03-25 11:10:14 -0400
  • 364678bde5 feat: Update llama.cpp Andrei Betlen 2024-03-24 12:27:49 -0400
  • d11ccc3036 fix(server): minor type fixes Andrei Betlen 2024-03-23 17:14:15 -0400
  • d3afd4507f
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-03-23 15:47:34 +0530
  • c1325dcdfb fix: tool_call missing first token. Andrei Betlen 2024-03-22 23:44:04 -0400
  • e325a831f0 feat: Update llama.cpp Andrei Betlen 2024-03-22 23:43:29 -0400
  • c89be28ef9 feat: Update llama.cpp Andrei Betlen 2024-03-20 20:50:47 -0400
  • 3db03b7302 feat: Update llama.cpp Andrei Betlen 2024-03-20 13:27:43 -0400
  • 740f3f3812
         fix: set LLAMA_METAL_EMBED_LIBRARY=on on MacOS arm64 (#1289) bretello 2024-03-20 17:46:09 +0100
  • f7decc9562 docs: Add chat examples to openapi ui Andrei Betlen 2024-03-19 10:52:53 -0400
  • 60d8498f21
         feat: Add tools/functions variables to Jinja2ChatFormatter, add function response formatting for all simple chat formats (#1273) Andrei 2024-03-19 04:55:57 -0400
  • 18d7ce918f feat: Update llama.cpp Andrei Betlen 2024-03-19 04:40:24 -0400
  • 7d4a5ec59f Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-03-18 11:37:33 -0400
  • bf64752535 chore: Bump version Andrei Betlen 2024-03-18 11:37:30 -0400
  • 8a60c7bc8c
         fix: Fix and optimize functionary chat handler (#1282) Jeffrey Fong 2024-03-18 22:40:57 +0800
  • 8d298b4750 feat: Update llama.cpp Andrei Betlen 2024-03-18 10:26:36 -0400
  • 4cb67f59d8
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-03-17 10:24:32 +0530
  • 6eb25231e4 feat: Update llama.cpp Andrei Betlen 2024-03-15 12:58:45 -0400
  • 20e6815252 fix: json mode Andrei Betlen 2024-03-15 12:58:34 -0400
  • 1a9b8af2dd feat: Update llama.cpp Andrei Betlen 2024-03-14 11:46:48 -0400
  • 4084aabe86 fix: set default pooling type to unspecified Andrei Betlen 2024-03-14 10:04:57 -0400
  • d318cc8b83 fix: Set default pooling_type to mean, check for null pointer. Andrei Betlen 2024-03-14 09:17:41 -0400
  • dd0ee56217 feat: Update llama.cpp Andrei Betlen 2024-03-13 15:57:35 -0400
  • 08e910f7a7 feat: Update llama.cpp Andrei Betlen 2024-03-10 23:45:05 -0400
  • dc23d15918
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-03-09 15:30:07 +0530
  • a7281994d8 chore: Bump version Andrei Betlen 2024-03-08 21:14:44 -0500
  • 919fca9f2b Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-03-08 21:10:56 -0500
  • d02a9cf16f Fixed json strings grammar by blacklisting character control set. Closes #1259 Andrei Betlen 2024-03-08 21:10:53 -0500
  • c139f8b5d5
         feat: Add endpoints for tokenize, detokenize and count tokens (#1136) Felipe Lorenz 2024-03-08 21:09:00 -0500
  • 1f3156d4f2
         fix: Check for existence of clip model path (#1264) Kevin Cao 2024-03-08 21:00:10 -0500
  • 2811014bae
         feat: Switch embed to llama_get_embeddings_seq (#1263) Douglas Hanley 2024-03-08 19:59:35 -0600
  • 40c6b54f68 feat: Update llama.cpp Andrei Betlen 2024-03-08 20:58:50 -0500
  • 93dc56ace8 Update llama.cpp Andrei Betlen 2024-03-06 01:32:00 -0500
  • 87a6e5797e feat: Update llama.cpp Andrei Betlen 2024-03-03 11:27:04 -0500
  • 13177aae0f chore: Bump version Andrei Betlen 2024-03-02 22:46:40 -0500
  • 663659f730
         docs: fix small typo in README: 'model know how' -> 'model knows how' (#1244) Kenneth Hoste 2024-03-03 04:20:41 +0100
  • 0e70984fb6 feat: Update llama.cpp Andrei Betlen 2024-03-02 22:20:04 -0500
  • d5df431278 chore: Bump version Andrei Betlen 2024-03-01 13:15:16 -0500
  • 97aa3a153d docs: Add information re: auto chat formats. Closes #1236 Andrei Betlen 2024-03-01 13:10:25 -0500
  • f062a7f51d feat: Update llama.cpp Andrei Betlen 2024-03-01 12:57:16 -0500
  • cf1fdd8a9a
         docs: fix typo in README.md embeddings example. (#1232) Douglas Hanley 2024-02-29 12:55:50 -0600
  • eebae1a368
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-02-29 21:11:35 +0530
  • 8c71725d53 fix: Remove deprecated cfg sampling functions Andrei Betlen 2024-02-28 14:37:07 -0500
  • 727d60c28a misc: Format Andrei Betlen 2024-02-28 14:27:40 -0500
  • 0d37ce52b1 feat: Update llama.cpp Andrei Betlen 2024-02-28 14:27:16 -0500
  • ffcd4b2636 chore: Bump version Andrei Betlen 2024-02-28 01:38:32 -0500
  • c36ab15e68
         fix: eos/bos_token set correctly for Jinja2ChatFormatter and automatic chat formatter (#1230) Sigbjørn Skjæret 2024-02-28 07:30:31 +0100
  • fea33c9b94 feat: Update llama.cpp Andrei Betlen 2024-02-27 12:22:17 -0500
  • f343259cf7
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-02-27 17:59:39 +0530
  • 4d574bd765
         feat(server): Add support for pulling models from Huggingface Hub (#1222) Andrei 2024-02-26 14:35:08 -0500
  • b3e358dee4 docs: Add example of local image loading to README Andrei Betlen 2024-02-26 11:58:33 -0500
  • afe1e445c9 chore: Bump version Andrei Betlen 2024-02-26 11:43:24 -0500
  • 9558ce7878 feat: Update llama.cpp Andrei Betlen 2024-02-26 11:40:58 -0500
  • a57d5dff86 feat: Update llama.cpp Andrei Betlen 2024-02-26 11:37:43 -0500
  • 79c649c2d1 docs: Update multimodal example Andrei Betlen 2024-02-26 11:34:45 -0500
  • bf315ee7a9 docs: Update multimodal example Andrei Betlen 2024-02-26 11:32:11 -0500
  • dbaba3059d fix: positional arguments only for low-level api Andrei Betlen 2024-02-26 11:31:11 -0500
  • 78e536dcfe fix: typo Andrei Betlen 2024-02-26 11:14:26 -0500
  • 44558cbd7a misc: llava_cpp use ctypes function decorator for binding Andrei Betlen 2024-02-26 11:07:33 -0500
  • 8383a9e562 fix: llava this function takes at least 4 arguments (0 given) Andrei Betlen 2024-02-26 11:03:20 -0500
  • 34111788fe feat: Update llama.cpp Andrei Betlen 2024-02-26 10:58:41 -0500
  • 5fc4c1efb6 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-02-25 21:15:54 -0500
  • 8e03fd9957 chore: Bump version Andrei Betlen 2024-02-25 21:14:01 -0500
  • e857c133fb feat: Update llama.cpp Andrei Betlen 2024-02-25 21:14:01 -0500
  • 252e1ff2b4 docs(examples): Add huggingface pull example Andrei Betlen 2024-02-25 21:09:41 -0500
  • bd4ec2e612 docs(examples): Add gradio chat example Andrei Betlen 2024-02-25 21:09:13 -0500
  • dcf38f6141 fix: remove prematurely commited change Andrei Betlen 2024-02-25 21:00:37 -0500
  • cbbcd888af feat: Update llama.cpp Andrei Betlen 2024-02-25 20:52:14 -0500
  • 19234aa0db fix: Restore type hints for low-level api Andrei Betlen 2024-02-25 16:54:37 -0500
  • 2292af5796 feat: Update llama.cpp Andrei Betlen 2024-02-25 16:53:58 -0500
  • 221edb9ef1 feat: Update llama.cpp Andrei Betlen 2024-02-24 23:47:29 -0500
  • 20ea6fd7d6 chore: Bump version Andrei Betlen 2024-02-23 12:38:36 -0500
  • b681674bf2 docs: Fix functionary repo_id Andrei Betlen 2024-02-23 12:36:13 -0500
  • f94faab686 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-02-23 12:34:03 -0500
  • 702306b381 docs: Restore functionary docs in README Andrei Betlen 2024-02-23 12:34:02 -0500
  • bce6dc0ac2
         docs: Update Functionary OpenAI Server Readme (#1193) Jeffrey Fong 2024-02-24 01:24:10 +0800
  • 47bad30dd7 fix: LlamaHFTokenizer now receives pre_tokens Andrei Betlen 2024-02-23 12:23:24 -0500
  • ded5d627a5 chore: Bump version Andrei Betlen 2024-02-23 11:32:43 -0500
  • 858496224e
         feat: Auto detect Mixtral's slightly different format (#1214) Luke Stanley 2024-02-23 16:27:38 +0000
  • db776a885c fix: module 'llama_cpp.llama_cpp' has no attribute 'c_uint8' Andrei Betlen 2024-02-23 11:24:53 -0500
  • da343412ee
         Merge https://github.com/abetlen/llama-cpp-python baalajimaestro 2024-02-23 18:03:03 +0530
  • 427d816ebf chore: Bump version Andrei Betlen 2024-02-23 04:54:08 -0500
  • 52d9d70076
         docs: Update README.md to fix pip install llama cpp server (#1187) Aditya Purandare 2024-02-23 15:11:22 +0530
  • 251a8a2cad
         feat: Add Google's Gemma formatting via chat_format="gemma" (#1210) Alvaro Bartolome 2024-02-23 18:40:52 +0900
  • eebb102df7 feat: Update llama.cpp Andrei Betlen 2024-02-23 03:42:08 -0500
  • 5f96621e92 misc: only search tests folder for tests Andrei Betlen 2024-02-23 03:40:25 -0500
  • b9aca612af misc: use typesafe byref for internal classes Andrei Betlen 2024-02-23 03:40:07 -0500
  • a0ce429dc0 misc: use decorator to bind low level api functions, fixes docs Andrei Betlen 2024-02-23 03:39:38 -0500
  • 410e02da51 docs: Fix typo Andrei Betlen 2024-02-23 00:43:31 -0500
  • eb56ce2e2a docs: fix low-level api example Andrei Betlen 2024-02-22 11:33:05 -0500
  • 0f8cad6cb7 docs: Update README Andrei Betlen 2024-02-22 11:31:44 -0500
  • 045cc12670 docs: Update README Andrei Betlen 2024-02-22 03:53:52 -0500
  • e10af30cf1 fix: TypeAlias import error Andrei Betlen 2024-02-22 03:27:28 -0500
  • 3561ebf536 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python into main Andrei Betlen 2024-02-22 03:25:13 -0500