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

Commit graph

  • a5aa6c1478 llama_cpp server: add missing top_k param to CreateChatCompletionRequest Lucas Doyle 2023-04-29 11:52:20 -0700
  • 1e42913599 llama_cpp server: move logprobs to supported Lucas Doyle 2023-04-29 11:48:49 -0700
  • b47b9549d5 llama_cpp server: delete some ignored / unused parameters Lucas Doyle 2023-04-29 01:19:30 -0700
  • e40fcb0575 llama_cpp server: mark model as required Lucas Doyle 2023-04-29 00:47:35 -0700
  • 9d60ae56f2 Fix whitespace Andrei Betlen 2023-05-01 18:07:45 -0400
  • 53c0129eb6 Update submoduele clone instructions Andrei Betlen 2023-05-01 18:07:15 -0400
  • b6747f722e Fix logprob calculation. Fixes #134 Andrei Betlen 2023-05-01 17:45:08 -0400
  • c088a2b3a7 Un-skip tests Andrei Betlen 2023-05-01 15:46:03 -0400
  • bf3d0dcb2c Fix tests Andrei Betlen 2023-05-01 15:28:46 -0400
  • 5034bbf499 Bump version Andrei Betlen 2023-05-01 15:23:59 -0400
  • f073ef0571 Update llama.cpp Andrei Betlen 2023-05-01 15:23:01 -0400
  • 9ff9cdd7fc Fix import error Andrei Betlen 2023-05-01 15:11:15 -0400
  • 2f8a3adaa4 Temporarily skip sampling tests. Andrei Betlen 2023-05-01 15:01:49 -0400
  • dbe0ad86c8 Update test dependencies Andrei Betlen 2023-05-01 14:50:01 -0400
  • 350a1769e1 Update sampling api Andrei Betlen 2023-05-01 14:47:55 -0400
  • 7837c3fdc7 Fix return types and import comments Andrei Betlen 2023-05-01 14:02:06 -0400
  • 55d6308537 Fix test dependencies Andrei Betlen 2023-05-01 11:39:18 -0400
  • ccf1ed54ae Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-05-01 11:35:14 -0400
  • 79ba9ed98d
         Merge pull request #125 from Stonelinks/app-server-module-importable Andrei 2023-05-01 11:31:08 -0400
  • 80184a286c Update llama.cpp Andrei Betlen 2023-05-01 10:44:28 -0400
  • efe8e6f879 llama_cpp server: slight refactor to init_llama function Lucas Doyle 2023-04-28 23:47:36 -0700
  • 6d8db9d017 tests: simple test for server module Lucas Doyle 2023-04-28 23:26:07 -0700
  • 468377b0e2 llama_cpp server: app is now importable, still runnable as a module Lucas Doyle 2023-04-28 22:43:37 -0700
  • 755f9fa455
         Merge pull request #118 from SagsMug/main Andrei 2023-04-29 07:19:01 -0400
  • 18a0c10032 Remove excessive errors="ignore" and add utf8 test Mug 2023-04-29 12:19:22 +0200
  • 523825e91d Update README Andrei Betlen 2023-04-28 17:12:03 -0400
  • e00beb13b5 Update README Andrei Betlen 2023-04-28 17:08:18 -0400
  • 5423d047c7 Bump version Andrei Betlen 2023-04-28 15:33:08 -0400
  • ea0faabae1 Update llama.cpp Andrei Betlen 2023-04-28 15:32:43 -0400
  • b7d14efc8b Python weirdness Mug 2023-04-28 13:20:31 +0200
  • eed61289b6 Dont detect off tokens, detect off detokenized utf8 Mug 2023-04-28 13:16:18 +0200
  • 3a98747026 One day, i'll fix off by 1 errors permanently too Mug 2023-04-28 12:54:28 +0200
  • c39547a986 Detect multi-byte responses and wait Mug 2023-04-28 12:50:30 +0200
  • 9339929f56 Update llama.cpp Andrei Betlen 2023-04-26 20:00:54 -0400
  • 5f81400fcb Also ignore errors on input prompts Mug 2023-04-26 14:45:51 +0200
  • 3c130f00ca Remove try catch from chat Mug 2023-04-26 14:38:53 +0200
  • be2c961bc9 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python Mug 2023-04-26 14:38:09 +0200
  • c4a8491d42 Fix decode errors permanently Mug 2023-04-26 14:37:06 +0200
  • cbd26fdcc1 Update llama.cpp Andrei Betlen 2023-04-25 19:03:41 -0400
  • 3cab3ef4cb Update n_batch for server Andrei Betlen 2023-04-25 09:11:32 -0400
  • cc706fb944 Add ctx check and re-order __init__. Closes #112 Andrei Betlen 2023-04-25 09:00:53 -0400
  • 996e31d861 Bump version Andrei Betlen 2023-04-25 01:37:07 -0400
  • 848c83dfd0 Add FORCE_CMAKE option Andrei Betlen 2023-04-25 01:36:37 -0400
  • 9dddb3a607 Bump version Andrei Betlen 2023-04-25 00:19:44 -0400
  • d484c5634e Bugfix: Check cache keys as prefix to prompt tokens Andrei Betlen 2023-04-24 22:18:54 -0400
  • b75fa96bf7 Update docs Andrei Betlen 2023-04-24 19:56:57 -0400
  • cbe95bbb75 Add cache implementation using llama state Andrei Betlen 2023-04-24 19:54:41 -0400
  • 2c359a28ff Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-04-24 17:51:27 -0400
  • 197cf80601 Add save/load state api for Llama class Andrei Betlen 2023-04-24 17:51:25 -0400
  • c4c332fc51 Update llama.cpp Andrei Betlen 2023-04-24 17:42:09 -0400
  • 280a047dd6 Update llama.cpp Andrei Betlen 2023-04-24 15:52:24 -0400
  • 86f8e5ad91 Refactor internal state for Llama class Andrei Betlen 2023-04-24 15:47:54 -0400
  • f37456133a
         Merge pull request #108 from eiery/main Andrei 2023-04-24 13:48:09 -0400
  • 02cf881317 Update llama.cpp Andrei Betlen 2023-04-24 09:30:10 -0400
  • 8476b325f1
         Change to bullseye Niek van der Maas 2023-04-24 09:54:38 +0200
  • aa12d8a81f
         Update llama.py eiery 2023-04-23 20:56:40 -0400
  • 7230599593 Disable mmap when applying lora weights. Closes #107 Andrei Betlen 2023-04-23 14:53:17 -0400
  • e99caedbbd Update llama.cpp Andrei Betlen 2023-04-22 19:50:28 -0400
  • 643b73e155 Bump version Andrei Betlen 2023-04-21 19:38:54 -0400
  • 1eb130a6b2 Update llama.cpp Andrei Betlen 2023-04-21 17:40:27 -0400
  • ba3959eafd Update llama.cpp Andrei Betlen 2023-04-20 05:15:31 -0400
  • 207adbdf13 Bump version Andrei Betlen 2023-04-20 01:48:24 -0400
  • 3d290623f5 Update llama.cpp Andrei Betlen 2023-04-20 01:08:15 -0400
  • e4647c75ec Add use_mmap flag to server Andrei Betlen 2023-04-19 15:57:46 -0400
  • 207ebbc8dc Update llama.cpp Andrei Betlen 2023-04-19 14:02:11 -0400
  • 0df4d69c20 If lora base is not set avoid re-loading the model by passing NULL Andrei Betlen 2023-04-18 23:45:25 -0400
  • 95c0dc134e Update type signature to allow for null pointer to be passed. Andrei Betlen 2023-04-18 23:44:46 -0400
  • 453e517fd5 Add seperate lora_base path for applying LoRA to quantized models using original unquantized model weights. Andrei Betlen 2023-04-18 10:20:46 -0400
  • 32ca803bd8 Merge branch 'main' of github.com:abetlen/llama_cpp_python into main Andrei Betlen 2023-04-18 02:22:39 -0400
  • b2d44aa633 Update llama.cpp Andrei Betlen 2023-04-18 02:22:35 -0400
  • 4ce6670bbd
         Merge pull request #87 from SagsMug/main Andrei 2023-04-18 02:11:40 -0400
  • eb7f278cc6 Add lora_path parameter to Llama model Andrei Betlen 2023-04-18 01:43:44 -0400
  • 35abf89552 Add bindings for LoRA adapters. Closes #88 Andrei Betlen 2023-04-18 01:30:04 -0400
  • 3f68e95097 Update llama.cpp Andrei Betlen 2023-04-18 01:29:27 -0400
  • 1b73a15e62 Merge branch 'main' of https://github.com/abetlen/llama-cpp-python Mug 2023-04-17 14:45:42 +0200
  • 53d17ad003 Fixed end of text wrong type, and fix n_predict behaviour Mug 2023-04-17 14:45:28 +0200
  • b2a24bddac Update docs Andrei Betlen 2023-04-15 22:31:14 -0400
  • e38485a66d Bump version. Andrei Betlen 2023-04-15 20:27:55 -0400
  • 89856ef00d Bugfix: only eval new tokens Andrei Betlen 2023-04-15 17:32:53 -0400
  • 6df27b2da0 Merge branch 'main' of github.com:abetlen/llama-cpp-python Niek van der Maas 2023-04-15 20:24:59 +0200
  • 59b37bbbd2 Support openblas Niek van der Maas 2023-04-15 20:24:46 +0200
  • 887f3b73ac Update llama.cpp Andrei Betlen 2023-04-15 12:16:05 -0400
  • 92c077136d Add experimental cache Andrei Betlen 2023-04-15 12:03:09 -0400
  • a6372a7ae5 Update stop sequences for chat Andrei Betlen 2023-04-15 12:02:48 -0400
  • 83b2be6dc4 Update chat parameters Andrei Betlen 2023-04-15 11:58:43 -0400
  • 62087514c6 Update chat prompt Andrei Betlen 2023-04-15 11:58:19 -0400
  • 02f9fb82fb Bugfix Andrei Betlen 2023-04-15 11:39:52 -0400
  • 3cd67c7bd7 Add type annotations Andrei Betlen 2023-04-15 11:39:21 -0400
  • d7de0e8014 Bugfix Andrei Betlen 2023-04-15 00:08:04 -0400
  • e90e122f2a Use clear Andrei Betlen 2023-04-14 23:33:18 -0400
  • ac7068a469 Track generated tokens internally Andrei Betlen 2023-04-14 23:33:00 -0400
  • 25b646c2fb Update llama.cpp Andrei Betlen 2023-04-14 23:32:05 -0400
  • 6e298d8fca Set kv cache size to f16 by default Andrei Betlen 2023-04-14 22:21:19 -0400
  • 9c8c2c37dc Update llama.cpp Andrei Betlen 2023-04-14 10:01:57 -0400
  • 6c7cec0c65 Fix completion request Andrei Betlen 2023-04-14 10:01:15 -0400
  • 6153baab2d Clean up logprobs implementation Andrei Betlen 2023-04-14 09:59:33 -0400
  • 26cc4ee029 Fix signature for stop parameter Andrei Betlen 2023-04-14 09:59:08 -0400
  • 7dc0838fff Bump version Andrei Betlen 2023-04-13 00:35:05 -0400
  • 6595ad84bf Add field to disable reseting between generations Andrei Betlen 2023-04-13 00:28:00 -0400
  • 22fa5a621f Revert "Deprecate generate method" Andrei Betlen 2023-04-13 00:19:55 -0400