Commit Graph

28 Commits

Author SHA1 Message Date
matatonic
309b72e549
[extension/openai] add edits & image endpoints & fix prompt return in non --chat modes (#1935) 2023-05-11 11:06:39 -03:00
oobabooga
b7a589afc8 Improve the Metharme prompt 2023-05-10 16:09:32 -03:00
oobabooga
bdf1274b5d Remove duplicate code 2023-05-10 01:34:04 -03:00
oobabooga
ba445cf59f Fix some galactica templates 2023-05-09 22:58:59 -03:00
minipasila
334486f527
Added instruct-following template for Metharme (#1679) 2023-05-09 22:29:22 -03:00
Carl Kenner
814f754451
Support for MPT, INCITE, WizardLM, StableLM, Galactica, Vicuna, Guanaco, and Baize instruction following (#1596) 2023-05-09 20:37:31 -03:00
Wojtab
e9e75a9ec7
Generalize multimodality (llava/minigpt4 7b and 13b now supported) (#1741) 2023-05-09 20:18:02 -03:00
oobabooga
00e333d790 Add MOSS support 2023-05-04 23:20:34 -03:00
oobabooga
0e6d17304a Clearer syntax for instruction-following characters 2023-05-03 22:50:39 -03:00
oobabooga
91745f63c3 Use Vicuna-v0 by default for Vicuna models 2023-04-26 17:45:38 -03:00
oobabooga
93e5c066ae Update RWKV Raven template 2023-04-26 17:31:03 -03:00
oobabooga
1d8b8222e9 Revert #1579, apply the proper fix
Apparently models dislike trailing spaces.
2023-04-26 16:47:50 -03:00
TiagoGF
a941c19337
Fixing Vicuna text generation (#1579) 2023-04-26 16:20:27 -03:00
oobabooga
a777c058af
Precise prompts for instruct mode 2023-04-26 03:21:53 -03:00
Wojtab
12212cf6be
LLaVA support (#1487) 2023-04-23 20:32:22 -03:00
Forkoz
c6fe1ced01
Add ChatGLM support (#1256)
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
2023-04-16 19:15:03 -03:00
oobabooga
cb95a2432c Add Koala support 2023-04-16 14:41:06 -03:00
OWKenobi
310bf46a94
Instruction Character Vicuna, Instruction Mode Bugfix (#838) 2023-04-06 17:40:44 -03:00
oobabooga
e722c240af Add Instruct mode 2023-04-05 13:54:50 -03:00
oobabooga
38afc2470c
Change indentation 2023-04-04 16:32:27 -03:00
oobabooga
881dbc3d44
Add back the name 2023-04-04 13:11:34 -03:00
Alex "mcmonkey" Goodwin
165d757444 improve the example character yaml format - use multiline blocks
multiline blocks make the input much cleaner and simpler, particularly for the example_dialogue. For the greeting block it can kinda go either way but I think it still ends up nicer. Also double quotes in context fixes the need to escape the singlequote inside.
2023-04-04 08:25:11 -07:00
TheTerrasque
2157bb4319
New yaml character format (#337 from TheTerrasque/feature/yaml-characters)
This doesn't break backward compatibility with JSON characters.
2023-04-02 20:34:25 -03:00
oobabooga
c472c34818 Change Chiharu's example dialogue definition format 2023-02-28 01:13:58 -03:00
oobabooga
afc2b0f4c8 Remove .gitignore 2023-02-02 12:42:49 -03:00
81300
a97afa6965
Add DeepSpeed ZeRO-3 integration 2023-02-01 18:48:13 +02:00
oobabooga
2181fca709 Better defaults for chat 2023-01-19 18:58:45 -03:00
oobabooga
8d788874d7 Add support for characters 2023-01-19 16:46:46 -03:00