47 Commits

Author	SHA1	Message	Date
oobabooga	00ab450c13	Multiple histories for each character (#4022)	2023-09-21 17:19:32 -03:00
oobabooga	c237ce607e	Move characters/instruction-following to instruction-templates	2023-08-06 17:50:32 -07:00
matatonic	32e7cbb635	More models: +StableBeluga2 (#3415)	2023-08-03 16:02:54 -03:00
CrazyShipOne	40038fdb82	add chat instruction config for BaiChuan model (#3332)	2023-08-01 22:25:20 -03:00
oobabooga	c8a59d79be	Add a template for NewHope	2023-08-01 13:27:29 -07:00
oobabooga	5ca37765d3	Only replace {{user}} and {{char}} at generation time	2023-07-30 11:42:30 -07:00
oobabooga	6e16af34fd	Save uploaded characters as yaml ... Also allow yaml characters to be uploaded directly	2023-07-30 11:25:38 -07:00
oobabooga	193c6be39c	Add missing \n to llama-v2 template context	2023-07-26 08:26:56 -07:00
oobabooga	8ec225f245	Add EOS/BOS tokens to Llama-2 template ... Following this comment: https://github.com/ggerganov/llama.cpp/issues/2262#issuecomment-1641063329	2023-07-18 15:35:27 -07:00
oobabooga	e0631e309f	Create instruction template for Llama-v2 (#3194)	2023-07-18 17:19:18 -03:00
oobabooga	656b457795	Add Airoboros-v1.2 template	2023-07-17 07:27:42 -07:00
matatonic	68ae5d8262	more models: +orca_mini (#2859)	2023-06-25 01:54:53 -03:00
matatonic	d94ea31d54	more models. +minotaur 8k (#2806)	2023-06-21 21:05:08 -03:00
matatonic	90be1d9fe1	More models (match more) & templates (starchat-beta, tulu) (#2790)	2023-06-21 12:30:44 -03:00
matatonic	2220b78e7a	models/config.yaml: +alpacino, +alpasta, +hippogriff, +gpt4all-snoozy, +lazarus, +based, -airoboros 4k (#2580)	2023-06-17 19:14:25 -03:00
FartyPants	ac40c59ac3	Added Guanaco-QLoRA to Instruct character (#2574)	2023-06-08 12:24:32 -03:00
oobabooga	f344ccdddb	Add a template for bluemoon	2023-06-01 14:42:12 -03:00
Carl Kenner	a9733d4a99	Metharme context fix (#2153)	2023-05-19 11:46:13 -03:00
Carl Kenner	c86231377b	Wizard Mega, Ziya, KoAlpaca, OpenBuddy, Chinese-Vicuna, Vigogne, Bactrian, H2O support, fix Baize (#2159)	2023-05-19 11:42:41 -03:00
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