Commit Graph

75 Commits

Author SHA1 Message Date
josc146
994fc7c828 fix cross-device state cache exception 2023-07-11 11:20:12 +08:00
josc146
f9f1d5c9fc improve /completions api compatibility 2023-07-10 20:45:08 +08:00
josc146
6fbb86667c improve python script error messages 2023-07-07 20:16:35 +08:00
josc146
987854fe49 lora finetune (need to be refactored) 2023-07-03 17:41:47 +08:00
josc146
417389c5f6 improve for python3.8 3.9 2023-06-29 20:12:11 +08:00
josc146
9ed3547738 rwkv pip 0.8.0 2023-06-28 19:36:15 +08:00
josc146
131a7ddf4a fix the prompt cache that contains potential error 2023-06-21 16:07:16 +08:00
josc146
43bc08648d update manifest 2023-06-20 16:07:52 +08:00
josc146
e93c77394d add usage 2023-06-20 15:55:52 +08:00
josc146
8963543159 embeddings api compatible with openai api and langchain(sdk) 2023-06-19 22:51:06 +08:00
josc146
377f71b16b type 2023-06-19 22:32:02 +08:00
josc146
d32351c130 exact model name 2023-06-19 22:30:49 +08:00
josc146
967be6f88f refactor completions api 2023-06-18 20:16:52 +08:00
josc146
721653a812 fix the state cache crash caused by bad prompts 2023-06-15 22:37:00 +08:00
josc146
21c3009945 improve api docs 2023-06-15 21:52:22 +08:00
josc146
51c5696bb9 improve python dependencies installation 2023-06-14 22:21:17 +08:00
josc146
714b8834c7 chore 2023-06-13 22:47:17 +08:00
josc146
5896593951 max_trie_len 2023-06-12 15:22:17 +08:00
josc146
8431b5d24f log Generation Prompt 2023-06-12 13:41:51 +08:00
josc146
bbd1ac1484 allow unloading model with switch-model 2023-06-12 12:34:03 +08:00
josc146
5990567a79 avoid misoperations of state_cache 2023-06-12 12:32:50 +08:00
josc146
fa0fcc2c89 add support for python3.8 3.9 2023-06-12 12:09:23 +08:00
josc146
cea1d8b4d1 add logs for state cache and switch-model 2023-06-09 20:46:19 +08:00
josc146
635767408f fix UnboundLocalError: local variable 'response' referenced before assignment 2023-06-08 13:30:34 +08:00
josc146
9bd9b9ecbd add requirements_without_cyac.txt 2023-06-05 22:58:56 +08:00
josc146
4e75531651 fix the crash issue caused by temperature being 0 2023-06-04 11:53:33 +08:00
josc146
edc6ac7297 chore 2023-06-03 20:34:33 +08:00
josc146
966b912013 improve logs 2023-06-03 19:28:37 +08:00
josc146
dc71054e61 improve logs 2023-06-03 17:36:50 +08:00
josc146
38b775c937 add logs 2023-06-03 17:12:59 +08:00
josc146
b41a2e7039 move state cache to memory (todo: state cache db) 2023-06-02 21:33:57 +08:00
josc146
b63370928d macOS 2023-06-01 16:54:21 +08:00
josc146
2f5a7d2d51 fix_tokens 2023-05-31 16:07:09 +08:00
josc146
cf16e54463 fix_tokens 2023-05-31 14:55:13 +08:00
josc146
c8b2bb53ef improve system for rwkv-4-world 2023-05-31 12:46:06 +08:00
josc146
8291c50058 safe ModelConfigBody 2023-05-30 23:13:27 +08:00
josc146
9945338458 chore 2023-05-30 11:52:33 +08:00
josc146
53b6a5ffe0 allow system to be placed anywhere 2023-05-29 22:26:22 +08:00
josc146
da033ab096 chore 2023-05-29 20:51:20 +08:00
josc146
142e30622e send response even token is END_OF_TEXT 2023-05-29 20:17:29 +08:00
josc146
55bb33bcbb embed all core dependencies 2023-05-29 20:14:42 +08:00
josc146
6fc5a335fb embed dependencies 2023-05-29 09:39:16 +08:00
josc146
fecdf238c1 feat: preload preset_system 2023-05-29 00:08:13 +08:00
josc146
3e11128c9d feat: use model state cache to achieve 5x - 50x faster preparation time for generation 2023-05-28 23:52:38 +08:00
josc146
94971bb666 support for rwkv-4-world 2023-05-28 12:53:14 +08:00
josc146
b7fb8ed898 improve api concurrency performance 2023-05-27 15:18:12 +08:00
josc146
06622b79aa update rwkv_generate 2023-05-25 20:34:42 +08:00
josc146
bb8af451f6 fix cuda40 kernel 2023-05-25 00:22:09 +08:00
josc146
77ce87d209 update cuda40 kernel 2023-05-24 22:18:14 +08:00
josc146
f439b3d382 add api host setting 2023-05-24 22:03:30 +08:00