547 Commits

Author	SHA1	Message	Date
oobabooga	185587a33e	Add a history size parameter to the chat ... If too many messages are used in the prompt, the model gets really slow. It is useful to have the ability to limit this.	2023-01-20 17:03:09 -03:00
oobabooga	78d5a999e6	Improve prompt formatation	2023-01-20 01:54:38 -03:00
oobabooga	70ff685736	Encode the input string correctly	2023-01-20 00:45:02 -03:00
oobabooga	b66d18d5a0	Allow presets/characters with '.' in their names	2023-01-19 21:56:33 -03:00
oobabooga	11c3214981	Fix some regexes	2023-01-19 19:59:34 -03:00
oobabooga	e61138bdad	Minor fixes	2023-01-19 19:04:54 -03:00
oobabooga	2181fca709	Better defaults for chat	2023-01-19 18:58:45 -03:00
oobabooga	83808171d3	Add --share option for Colab	2023-01-19 17:31:29 -03:00
oobabooga	8d788874d7	Add support for characters	2023-01-19 16:46:46 -03:00
oobabooga	3121f4788e	Fix uploading chat log in --chat mode	2023-01-19 15:05:42 -03:00
oobabooga	849e4c7f90	Better way of finding the generated reply in the output string	2023-01-19 14:57:01 -03:00
oobabooga	d03b0ad7a8	Implement saving/loading chat logs (#9)	2023-01-19 14:03:47 -03:00
oobabooga	39bfea5a22	Add a progress bar	2023-01-19 12:20:57 -03:00
oobabooga	5390fc87c8	add auto-devices when disk is used	2023-01-19 12:11:44 -03:00
oobabooga	759da435e3	Release 8-bit models memory	2023-01-19 12:03:16 -03:00
oobabooga	7ace04864a	Implement sending layers to disk with --disk (#10)	2023-01-19 11:09:24 -03:00
oobabooga	93fa9bbe01	Clean up the streaming implementation	2023-01-19 10:43:05 -03:00
oobabooga	c90310e40e	Small simplification	2023-01-19 00:41:57 -03:00
oobabooga	99536ef5bf	Add no-stream option	2023-01-18 23:56:42 -03:00
oobabooga	116299b3ad	Manual eos_token implementation	2023-01-18 22:57:39 -03:00
oobabooga	3cb30bed0a	Add a "stop" button	2023-01-18 22:44:47 -03:00
oobabooga	8f27d33034	Fix another bug	2023-01-18 22:08:23 -03:00
oobabooga	6c7f187586	Minor change	2023-01-18 21:59:23 -03:00
oobabooga	b3cba0b330	Bug	2023-01-18 21:54:44 -03:00
oobabooga	df2e910421	Stop generating in chat mode when \nYou: is generated	2023-01-18 21:51:18 -03:00
oobabooga	022960a087	This is the correct way of sampling 1 token at a time	2023-01-18 21:37:21 -03:00
oobabooga	0f01a3b1fa	Implement text streaming (#10) ... Still experimental. There might be bugs.	2023-01-18 19:06:50 -03:00
oobabooga	ca13acdfa0	Ensure that the chat prompt will always contain < 2048 tokens ... This way, we can keep the context string at the top of the prompt even if you keep talking to the bot for hours. Before this commit, the prompt would be simply truncated and the context string would eventually be lost.	2023-01-17 20:16:23 -03:00
oobabooga	6456777b09	Clean things up	2023-01-16 16:35:45 -03:00
oobabooga	3a99b2b030	Change a truncation parameter	2023-01-16 13:53:30 -03:00
oobabooga	54bf55372b	Truncate prompts to 2048 characters	2023-01-16 13:43:23 -03:00
oobabooga	c7a2818665	Grammar	2023-01-16 10:10:09 -03:00
oobabooga	d973897021	Typo	2023-01-16 01:52:28 -03:00
oobabooga	47a20638de	Don't need this	2023-01-15 23:15:30 -03:00
oobabooga	b55486fa00	Reorganize things	2023-01-15 23:01:51 -03:00
oobabooga	ebf4d5f506	Add --max-gpu-memory parameter for #7	2023-01-15 22:33:35 -03:00
oobabooga	bb1a172da0	Fix a bug in cai mode chat	2023-01-15 19:41:25 -03:00
oobabooga	e6691bd920	Make chat mode more like cai	2023-01-15 18:16:46 -03:00
oobabooga	e04ecd4bce	Minor improvements	2023-01-15 16:43:31 -03:00
oobabooga	027c3dd27d	Allow jpg profile images	2023-01-15 15:45:25 -03:00
oobabooga	afe9f77f96	Reorder parameters	2023-01-15 15:30:39 -03:00
oobabooga	88d67427e1	Implement default settings customization using a json file	2023-01-15 15:23:41 -03:00
oobabooga	6136da419c	Add --cai-chat option that mimics Character.AI's interface	2023-01-15 12:20:04 -03:00
oobabooga	13b04c1b94	Add "remove last message" button to chat	2023-01-15 03:19:09 -03:00
oobabooga	fd220f827f	Remove annoying warnings	2023-01-15 00:39:51 -03:00
oobabooga	d962e69496	Improve chat preprocessing	2023-01-14 23:50:34 -03:00
oobabooga	9a7f187b5a	Improve pygmalion line breaks	2023-01-14 23:26:14 -03:00
oobabooga	ecb2cc2194	Pygmalion: add checkbox for choosing whether to stop at newline or not	2023-01-13 15:02:17 -03:00
oobabooga	3a00cb1bbd	Reorganize GUI elements	2023-01-13 14:28:53 -03:00
oobabooga	3f1e70d2c8	Remove the temperature slider ... It was not being used by most presets.	2023-01-13 14:00:43 -03:00
oobabooga	7f93012a89	Add default names/context for pygmalion	2023-01-13 10:12:47 -03:00
oobabooga	9410486bd8	Enable the API ... Let's goooooooooooooo	2023-01-11 16:43:13 -03:00
oobabooga	66f73c1b32	Remove default text from output box	2023-01-11 01:36:11 -03:00
oobabooga	01ac065d7e	Implement Continue button	2023-01-11 01:33:57 -03:00
oobabooga	4b09e7e355	Sort models alphabetically	2023-01-11 01:17:20 -03:00
oobabooga	d5e01c80e3	Add nice HTML output for all models	2023-01-11 01:10:11 -03:00
oobabooga	b2a2ddcb15	Remove T5 support (it sucks)	2023-01-10 23:39:50 -03:00
oobabooga	a236b24d24	Add --auto-devices and --load-in-8bit options for #4	2023-01-10 23:16:33 -03:00
oobabooga	3aefcfd963	Grammar	2023-01-09 19:07:47 -03:00
oobabooga	6c178b1c91	Add --listen parameter	2023-01-09 19:05:36 -03:00
oobabooga	13836a37c8	Remove unused parameter	2023-01-09 17:23:43 -03:00
oobabooga	f0013ac8e9	Don't need that	2023-01-09 16:30:14 -03:00
oobabooga	00a12889e9	Refactor model loading function	2023-01-09 16:28:04 -03:00
oobabooga	980f8112a7	Small bug fix	2023-01-09 12:56:54 -03:00
oobabooga	a751d7e693	Don't require GPT-J to be installed to load gpt4chan	2023-01-09 11:39:13 -03:00
oobabooga	6cbfe19c23	Submit with Shift+Enter	2023-01-09 11:22:12 -03:00
oobabooga	0e67ccf607	Implement CPU mode	2023-01-09 10:58:46 -03:00
oobabooga	f2a548c098	Stop generating at \n in chat mode ... Makes it a lot more efficient.	2023-01-08 23:00:38 -03:00
oobabooga	a9280dde52	Increase chat height, reorganize things	2023-01-08 20:10:31 -03:00
oobabooga	b871f76aac	Better default for chat output length ... Ideally, generation should stop at '\n', but this feature is brand new on transformers (https://github.com/huggingface/transformers/pull/20727)	2023-01-08 15:00:02 -03:00
oobabooga	b801e0d50d	Minor changes	2023-01-08 14:37:43 -03:00
oobabooga	730c5562cc	Disable gradio analytics	2023-01-08 01:42:38 -03:00
oobabooga	493051d5d5	Chat improvements	2023-01-08 01:33:45 -03:00
oobabooga	4058b33fc9	Improve the chat experience	2023-01-08 01:10:02 -03:00
oobabooga	ef4e610d37	Re-enable the progress bar in notebook mode	2023-01-07 23:01:39 -03:00
oobabooga	c3a0d00715	Name the input box	2023-01-07 22:55:54 -03:00
oobabooga	f76bdadbed	Add chat mode	2023-01-07 22:52:46 -03:00
oobabooga	300a500c0b	Improve spacings	2023-01-07 19:11:21 -03:00
oobabooga	5345685ead	Make paths cross-platform (should work on Windows now)	2023-01-07 16:33:43 -03:00
oobabooga	342e756878	Better recognize the model sizes	2023-01-07 12:21:04 -03:00
oobabooga	62c4d9880b	Fix galactica equations (more)	2023-01-07 12:13:09 -03:00
oobabooga	eeb63b1b8a	Fix galactica equations	2023-01-07 01:56:21 -03:00
oobabooga	3aaf5fb4aa	Make NovelAI-Sphinx Moth the default preset	2023-01-07 00:49:47 -03:00
oobabooga	c7b29668a2	Add HTML support for gpt4chan	2023-01-06 23:14:08 -03:00
oobabooga	3d6a3aac73	Reorganize the layout	2023-01-06 22:05:37 -03:00
oobabooga	4c89d4ab29	Name the inputs	2023-01-06 20:26:47 -03:00
oobabooga	e5f547fc87	Implement notebook mode	2023-01-06 20:22:26 -03:00
oobabooga	f54a13929f	Load default model with --model flag	2023-01-06 19:56:44 -03:00
oobabooga	1da8d4a787	Remove a space	2023-01-06 02:58:09 -03:00
oobabooga	ee650343bc	Better defaults while loading models	2023-01-06 02:54:33 -03:00
oobabooga	9498dca748	Make model autodetect all gpt-neo and opt models	2023-01-06 02:31:54 -03:00
oobabooga	deefa2e86a	Add comments	2023-01-06 02:26:33 -03:00
oobabooga	c06d7d28cb	Autodetect available models	2023-01-06 02:06:59 -03:00
oobabooga	285032da36	Make model loading more transparent	2023-01-06 01:41:52 -03:00
oobabooga	c65bad40dc	Add support for presets	2023-01-06 01:33:21 -03:00
oobabooga	838f768437	Add files	2022-12-21 13:27:31 -03:00
oobabooga	dde76a962f	Initial commit	2022-12-21 13:17:06 -03:00