43 Commits

Author	SHA1	Message	Date
hoshi-hiyouga	5f72439a1d	Update tuner.py	2024-05-11 23:55:59 +08:00
hoshi-hiyouga	13851fb045	Update tuner.py	2024-05-11 23:54:53 +08:00
BUAADreamer	8b997e32fb	add push processor to hub	2024-05-09 14:05:19 +08:00
BUAADreamer	ef33856380	add mllm export	2024-05-08 22:50:42 +08:00
BUAADreamer	0ca1d1967d	modify export model	2024-05-08 10:36:36 +08:00
hiyouga	ed8f8be752	update api and support abort eval in webui	2024-05-04 15:59:15 +08:00
hiyouga	245fe47ece	update webui and add CLIs	2024-05-03 02:58:23 +08:00
hiyouga	e057c8de48	support mllm hf inference	2024-04-26 05:34:58 +08:00
hiyouga	232642a621	fix #3238	2024-04-12 14:28:11 +08:00
hiyouga	148bda353f	fix resize vocab at inference #3022	2024-04-03 18:14:24 +08:00
hiyouga	17bf8a2c3a	support ORPO	2024-03-31 18:29:50 +08:00
marko1616	eb178eaff3	Fix Llama model save for full param train	2024-03-30 23:45:04 +08:00
hiyouga	558a538724	tiny fix	2024-03-25 21:18:08 +08:00
marko1616	c8f0d99704	pass ruff check	2024-03-24 16:12:10 +08:00
marko1616	6f080fdba3	fix Llama lora merge crash	2024-03-24 03:06:11 +08:00
marko1616	51349ea1cc	fix Llama lora merge crash	2024-03-24 02:55:23 +08:00
marko1616	c1e2c4ea45	fix Llama lora merge crash	2024-03-24 02:44:35 +08:00
hiyouga	8e04794b2d	fix packages	2024-03-17 22:32:03 +08:00
hiyouga	6bc2c23b6d	fix export	2024-03-15 15:06:30 +08:00
hiyouga	6ebde4f23e	tiny fix	2024-03-14 21:19:06 +08:00
hiyouga	3b4a59bfb1	fix export	2024-03-14 18:17:01 +08:00
hiyouga	72367307df	improve lora+ impl.	2024-03-13 23:32:51 +08:00
hiyouga	e5edcf440f	fix export model	2024-03-05 11:05:41 +08:00
hiyouga	2bc30763e9	fix #2320	2024-01-24 16:19:18 +08:00
hoshi-hiyouga	662b9a9dcf	Update tuner.py	2024-01-21 12:39:38 +08:00
yhyu13	9cdbd3bfc8	Remove manully set use_cache; torch_dtype is not str, save model as bfloat16 used to fail;	2024-01-21 11:12:15 +08:00
hiyouga	638234ceee	format style	2024-01-20 20:15:56 +08:00
hiyouga	ddd48ce8ab	Update tuner.py	2024-01-18 15:06:02 +08:00
hiyouga	d9f1cae351	support function calling	2024-01-18 09:54:23 +08:00
hiyouga	42859f0734	support export push_to_hub #2183	2024-01-16 23:59:42 +08:00
hiyouga	05ed4e8028	improve model export	2024-01-09 22:26:24 +08:00
hiyouga	d2a676c8ba	improve model export	2024-01-05 18:51:49 +08:00
hiyouga	65c5b0477c	fix args	2023-12-28 18:47:19 +08:00
hiyouga	e165354fac	fix export format	2023-12-28 18:40:46 +08:00
hiyouga	7aad0b889d	support unsloth	2023-12-23 00:14:33 +08:00
hiyouga	3551171d49	update tips	2023-12-15 23:52:50 +08:00
hiyouga	439a26c276	fix #1770	2023-12-15 23:50:15 +08:00
hiyouga	3524aa1e58	support quantization in export model	2023-12-15 23:44:50 +08:00
hiyouga	475a3fa0f4	fix #1659	2023-11-28 20:52:28 +08:00
hiyouga	859a6ea942	support export size setting	2023-11-26 18:34:09 +08:00
hiyouga	9ea9380145	support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569	2023-11-20 22:52:11 +08:00
hiyouga	ce78303600	support full-parameter PPO	2023-11-16 02:08:04 +08:00
hiyouga	4736344eb1	disentangle model from tuner and rename modules	2023-11-15 16:29:09 +08:00