3654 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
oobabooga	5f4f38ca5d	Merge branch 'main' of github.com:oobabooga/text-generation-webui	2023-04-06 14:38:29 -03:00
oobabooga	ef0f748618	Prevent CPU version of Torch from being installed (#10 from jllllll/oobabooga-windows)	2023-04-06 13:54:14 -03:00
oobabooga	d9e7aba714	Update README.md	2023-04-06 13:42:24 -03:00
oobabooga	59058576b5	Remove unused requirement	2023-04-06 13:28:21 -03:00
oobabooga	eec3665845	Add instructions for updating requirements	2023-04-06 13:24:01 -03:00
oobabooga	03cb44fc8c	Add new llama.cpp library (2048 context, temperature, etc now work)	2023-04-06 13:12:14 -03:00
EyeDeck	39f3fec913	Broaden GPTQ-for-LLaMA branch support (#820)	2023-04-06 12:16:48 -03:00
oobabooga	8cd899515e	Change instruct html a bit	2023-04-06 12:00:20 -03:00
oobabooga	4a28f39823	Update README.md	2023-04-06 02:47:27 -03:00
oobabooga	158ec51ae3	Increase instruct mode padding	2023-04-06 02:20:52 -03:00
Alex "mcmonkey" Goodwin	0c7ef26981	Lora trainer improvements (#763)	2023-04-06 02:04:11 -03:00
oobabooga	5b301d9a02	Create a Model tab	2023-04-06 01:54:05 -03:00
oobabooga	4a400320dd	Clean up	2023-04-06 01:47:00 -03:00
oobabooga	e94ab5dac1	Minor fixes	2023-04-06 01:43:10 -03:00
Randell Miller	641646a801	Fix crash if missing instructions directory (#812)	2023-04-06 01:24:22 -03:00
oobabooga	3f3e42e26c	Refactor several function calls and the API	2023-04-06 01:22:15 -03:00
SDS	378d21e80c	Add LLaMA-Precise preset (#767)	2023-04-05 18:52:36 -03:00
jllllll	1e656bef25	Specifically target cuda 11.7 ver. of torch 2.0.0 ... Move conda-forge channel to global list of channels Hopefully prevents missing or incorrect packages	2023-04-05 16:52:05 -05:00
eiery	19b516b11b	fix link to streaming api example (#803)	2023-04-05 14:50:23 -03:00
oobabooga	7617ed5bfd	Add AMD instructions	2023-04-05 14:42:58 -03:00
oobabooga	770ef5744f	Update README	2023-04-05 14:38:11 -03:00
Forkoz	8203ce0cac	Stop character pic from being cached when changing chars or clearing. (#798) ... Tested on both FF and chromium	2023-04-05 14:25:01 -03:00
oobabooga	7f66421369	Fix loading characters	2023-04-05 14:22:32 -03:00
oobabooga	90141bc1a8	Fix saving prompts on Windows	2023-04-05 14:08:54 -03:00
oobabooga	cf2c4e740b	Disable gradio analytics globally	2023-04-05 14:05:50 -03:00
oobabooga	e722c240af	Add Instruct mode	2023-04-05 13:54:50 -03:00
oobabooga	3d6cb5ed63	Minor rewrite	2023-04-05 01:21:40 -03:00
oobabooga	f3a2e0b8a9	Disable pre_layer when the model type is not llama	2023-04-05 01:19:26 -03:00
oobabooga	ca8bb38949	Simplify gallery	2023-04-05 00:34:17 -03:00
catalpaaa	4ab679480e	allow quantized model to be loaded from model dir (#760)	2023-04-04 23:19:38 -03:00
oobabooga	ae1fe45bc0	One more cache reset	2023-04-04 23:15:57 -03:00
oobabooga	8ef89730a5	Try to better handle browser image cache	2023-04-04 23:09:28 -03:00
oobabooga	cc6c7a37f3	Add make_thumbnail function	2023-04-04 23:03:58 -03:00
oobabooga	80dfba05f3	Better crop/resize cached images	2023-04-04 22:52:15 -03:00
oobabooga	65d8a24a6d	Show profile pictures in the Character tab	2023-04-04 22:28:49 -03:00
oobabooga	f70a2e3ad4	Second attempt at fixing empty space	2023-04-04 18:30:34 -03:00
oobabooga	9c86acda67	Fix huge empty space in the Character tab	2023-04-04 18:07:34 -03:00
oobabooga	38afc2470c	Change indentation	2023-04-04 16:32:27 -03:00
oobabooga	b2ce7282a1	Use past transformers version #773	2023-04-04 16:11:42 -03:00
jllllll	5aaf771c7d	Add additional sanity check ... Add environment creation error Improve error visibility	2023-04-04 12:31:26 -05:00
OWKenobi	ee4547cd34	Detect "vicuna" as llama model type (#772)	2023-04-04 13:23:27 -03:00
oobabooga	881dbc3d44	Add back the name	2023-04-04 13:11:34 -03:00
oobabooga	af0cb283e4	improve the example character yaml format (#770 from mcmonkey4eva)	2023-04-04 12:52:21 -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
oobabooga	8de22ac82a	Merge character upload tabs	2023-04-03 18:01:45 -03:00
oobabooga	b24147c7ca	Document --pre_layer	2023-04-03 17:34:25 -03:00
oobabooga	4c9ed09270	Update settings template	2023-04-03 14:59:26 -03:00
dependabot[bot]	ad37f396fc	Bump rwkv from 0.7.1 to 0.7.2 (#747)	2023-04-03 14:29:57 -03:00
dependabot[bot]	18f756ada6	Bump gradio from 3.24.0 to 3.24.1 (#746)	2023-04-03 14:29:37 -03:00
Niels Mündler	7aab88bcc6	Give API extension access to all generate_reply parameters (#744) ... * Make every parameter of the generate_reply function parameterizable * Add stopping strings as parameterizable	2023-04-03 13:31:12 -03:00