draff e6c631aea4 Replace --load-in-4bit with --llama-bits ...

Replaces --load-in-4bit with a more flexible --llama-bits arg to allow for 2 and 3 bit models as well. This commit also fixes a loading issue with .pt files which are not in the root of the models folder

2023-03-10 21:36:45 +00:00

..

chat.py

Better handle <USER>

2023-03-05 17:01:47 -03:00

deepspeed_parameters.py

Fix deepspeed (oops)

2023-02-02 10:39:37 -03:00

extensions.py

Move bot_picture.py inside the extension

2023-02-25 03:00:19 -03:00

html_generator.py

Store thumbnails as files instead of base64 strings

2023-02-27 13:41:00 -03:00

models.py

Replace --load-in-4bit with --llama-bits

2023-03-10 21:36:45 +00:00

RWKV.py

Add proper streaming to RWKV

2023-03-07 18:17:56 -03:00

shared.py

Replace --load-in-4bit with --llama-bits

2023-03-10 21:36:45 +00:00

stopping_criteria.py

Improve the imports

2023-02-23 14:41:42 -03:00

text_generation.py

Fix encode() for RWKV

2023-03-07 23:15:46 -03:00

ui.py

Stop chat from flashing dark when processing

2023-03-03 13:19:13 -03:00