Commit Graph

109 Commits

Author SHA1 Message Date
josc146
46b3b285f5 upgrade packages 2023-10-25 17:07:40 +08:00
josc146
0005816c1d fix linux kernel (partial revert 68228a45) 2023-10-05 00:08:18 +08:00
josc146
68228a4552 rwkv5 pre-compiled kernel (for windows) 2023-10-03 13:39:07 +08:00
josc146
79851433f8 upgrade rwkv pip (0.8.13) 2023-10-03 13:33:55 +08:00
josc146
d7abe5f0d1 add pre-compiled beta cuda kernel (rwkv-beta==0.8.5, 40%+ faster for fp16) (thanks to #180, pre-compiled kernel of RTX 40 Series will be included later) 2023-09-18 23:02:49 +08:00
josc146
5e5e1e9651 custom tokenizer .txt support 2023-09-18 17:20:55 +08:00
josc146
a25965530c custom tokenizer (#77) 2023-09-16 00:34:11 +08:00
josc146
d7dcc90008 chore 2023-09-15 16:31:14 +08:00
josc146
df969fcfc6 upgrade cuda-beta 2023-09-15 16:30:11 +08:00
josc146
50ff7ef6bc always use requirements.txt 2023-08-27 23:52:52 +08:00
josc146
a24b78e8c3 python-backend: extra ChatCompletionBody params (raw, presystem);
add default_stop when stop is null
2023-08-27 21:21:11 +08:00
josc146
c8025f1cff allow message content to be empty 2023-08-27 21:02:54 +08:00
josc146
02d5d641d1 chore 2023-08-24 22:48:54 +08:00
josc146
ef53951a16 webgpu support 2023-08-16 23:07:58 +08:00
josc146
61cea2a784 add misc API (/models and /dashboard/billing/credit_grants) 2023-08-14 23:37:55 +08:00
josc146
8a13bd3c1e add rwkv-cuda-beta support (faster) 2023-08-14 22:07:15 +08:00
josc146
da68926e9c chore (AddStateBody class) 2023-08-13 21:27:29 +08:00
josc146
e0b7453883 allow multiple systems 2023-08-04 22:27:55 +08:00
josc146
91e2828a95 allow completions input to be null 2023-08-04 22:22:59 +08:00
josc146
b3e35a4cdd allow custom user_name and assistant_name (/chat/completions API) 2023-07-31 22:48:54 +08:00
josc146
8764c37b03 RWKVType 2023-07-31 22:46:13 +08:00
josc146
d12a173f39 global penalty 2023-07-31 22:02:28 +08:00
josc146
aecacde819 remove response field of completions api 2023-07-29 19:20:43 +08:00
josc146
3ef22239eb improve default ChatCompletion stop 2023-07-29 19:19:38 +08:00
josc146
719090cc8c improve python backend startup speed 2023-07-29 19:18:01 +08:00
josc146
9d89b6f4db fix params 2023-07-28 22:13:19 +08:00
josc146
d0fd480bd6 chore 2023-07-26 22:24:26 +08:00
josc146
1df345b5eb improve embeddings API results 2023-07-25 20:30:43 +08:00
josc146
77868c798b chore 2023-07-25 16:37:06 +08:00
josc146
f56748a941 improve python backend startup speed 2023-07-25 16:14:29 +08:00
josc146
29c5b1d804 add midi api 2023-07-25 16:11:17 +08:00
josc146
34095a6c36 support for stop array 2023-07-25 16:10:22 +08:00
josc146
05b9b42b56 add support for MIDI RWKV 2023-07-25 16:09:31 +08:00
josc146
9b3b06ab04 fix input with array type (#96, #107) 2023-07-17 12:59:45 +08:00
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