651 Commits

Author	SHA1	Message	Date
hoshi-hiyouga	388b705a8d	Merge pull request #2462 from mnmueller/main ... Enable Parsing of SlimOrca	2024-02-09 22:55:48 +08:00
hiyouga	54ea9684ed	improve fix tokenizer	2024-02-09 14:53:14 +08:00
Mark Mueller	1d3598afa1	Slim Orca data parsing	2024-02-08 19:32:20 +01:00
Mark Mueller	6703d0546d	Slim Orca data parsing	2024-02-08 17:56:18 +01:00
Mark Mueller	7f792dfede	Slim Orca data parsing	2024-02-08 17:54:18 +01:00
Mark Mueller	8bd4182609	Slim Orca data parsing	2024-02-08 17:52:36 +01:00
Mark Mueller	36d7a75966	SlimOrca aligner	2024-02-08 08:28:32 -08:00
hoshi-hiyouga	d0daaa01f9	Merge pull request #2423 from mayflower/main ... Support for german sft and dpo	2024-02-07 15:58:20 +08:00
hiyouga	88a1bc9773	lint	2024-02-07 01:10:04 +08:00
hiyouga	0ae9a16b9d	update gc kwargs	2024-02-07 00:38:24 +08:00
hiyouga	ebf31b62eb	fix #2438	2024-02-06 15:23:08 +08:00
hiyouga	85622ae757	add models	2024-02-06 14:57:23 +08:00
hiyouga	ccabb5b04a	support qwen1.5	2024-02-06 00:10:51 +08:00
Johann-Peter Hartmann	1ecea9de63	Merge branch 'hiyouga:main' into main	2024-02-04 13:55:00 +00:00
hiyouga	3dc86c4af9	fix #2421	2024-02-04 21:02:55 +08:00
Johann-Peter Hartmann	63da6294dd	Merge branch 'hiyouga:main' into main	2024-02-04 12:51:25 +00:00
hiyouga	db0ab4d601	fix reserved label len	2024-02-04 17:54:26 +08:00
hiyouga	19d33ede13	fix #2420	2024-02-04 15:51:47 +08:00
hiyouga	b988ce0a0c	fix #2189	2024-02-04 00:47:37 +08:00
hiyouga	38e63bfd28	bump up transformers version	2024-02-04 00:01:16 +08:00
hiyouga	51df865734	fix #2397	2024-02-03 23:45:31 +08:00
hiyouga	6545c02790	add hint for freeze #2412	2024-02-03 23:38:56 +08:00
hiyouga	4ecadc3512	fix #2376	2024-02-03 23:14:31 +08:00
hiyouga	901faa16cc	support minicpm #2404	2024-02-03 22:36:46 +08:00
Johann-Peter Hartmann	b0ffde6e98	add simple german chatml template chatml_de	2024-02-03 09:01:15 +01:00
Fallen Angel	3399c0d645	fix eos_token_id=0 bug ... when eos_token_id=0, will never add eos_token	2024-02-02 17:34:48 +08:00
hiyouga	39bd5bd524	fix #2388	2024-01-31 17:23:56 +08:00
hiyouga	521ad76552	fix autoset attn impl, update data readme	2024-01-31 11:58:07 +08:00
hiyouga	2bc30763e9	fix #2320	2024-01-24 16:19:18 +08:00
ldwang	c284665425	Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3. ... Signed-off-by: ldwang <ftgreat@gmail.com>	2024-01-24 15:25:31 +08:00
ldwang	18923b1402	Add patch_mixtral_replace_moe_impl for full training Mitral using DeepSpeed Zero3. ... Signed-off-by: ldwang <ftgreat@gmail.com>	2024-01-24 14:43:16 +08:00
hiyouga	e4ba1deedf	add hint	2024-01-22 23:32:01 +08:00
hoshi-hiyouga	8e4b3a959a	Merge pull request #2283 from A-Cepheus/main ... fix: ZeRO3 does not work with MoE models	2024-01-22 23:28:45 +08:00
hoshi-hiyouga	bdc9eff635	Update patcher.py	2024-01-22 23:27:39 +08:00
hiyouga	b2fb0eca56	fix #2282 and update tool prompt	2024-01-22 22:27:30 +08:00
hiyouga	6fc2d5cc03	add orion models	2024-01-22 21:26:53 +08:00
A-Cepheus	b06a31e76a	🐞 fix: typo	2024-01-22 16:04:39 +08:00
A-Cepheus	319a72b48d	🐞 fix: typo, move MoE fix to patcher	2024-01-22 16:01:58 +08:00
A-Cepheus	e1d5c98519	fix: ZeRO3 does not work with MoE models	2024-01-22 15:21:14 +08:00
hiyouga	486cc8d360	add array param format	2024-01-21 22:17:48 +08:00
hiyouga	f51d48ea08	fix api	2024-01-21 19:15:27 +08:00
hiyouga	e0a717aa3a	fix #2268	2024-01-21 14:11:38 +08:00
hiyouga	3bc301be02	tiny fix	2024-01-21 13:26:12 +08:00
hoshi-hiyouga	2533be5e2a	Merge branch 'main' into fix_export_model_dtype	2024-01-21 12:40:24 +08:00
hoshi-hiyouga	662b9a9dcf	Update tuner.py	2024-01-21 12:39:38 +08:00
hoshi-hiyouga	11f612deab	Merge pull request #2262 from fenglui/main ... fix torch_dtype check of export_model	2024-01-21 12:34:37 +08:00
hiyouga	3c1e256992	format	2024-01-21 12:34:17 +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
Aleksandr	ace7fd4e0a	add russian lang	2024-01-21 04:28:14 +03:00
fenglui	f7c5b2d105	fix torch_dtype check of export_model	2024-01-21 05:01:53 +08:00