37 Commits

Author	SHA1	Message	Date
root	96af309191	增加了qlora的reamd	2024-07-26 15:07:06 +08:00
root	65e0e2570a	增加了qlora的finetune	2024-07-26 14:57:46 +08:00
刘丹	80e506289a	修复了两个bug，一个是代码中存在两个generate函数，另外一个是<用户>问题<AI>这种格式没有用到该代码中去的bug	2024-06-27 21:17:26 +08:00
刘丹	de1b467e20	增加了一个专门为mlx的数据处理代码	2024-06-27 21:14:00 +08:00
刘丹	2e6b0171f7	修改了llama_factory_example/README.md	2024-06-27 17:22:14 +08:00
刘丹	d9a3d4dd28	修改了llama_factory_example/README.md	2024-06-27 17:22:08 +08:00
刘丹	d58e892a98	增加了llama_facoty的微调示例	2024-06-27 09:04:43 +08:00
刘丹	262840a805	修改了finetune中的默认模型的错误	2024-06-25 10:29:25 +08:00
root	f062357093	add autoawq example	2024-06-24 10:57:19 +08:00
root	b808010417	注释前加了空格，保持代码规范性，刘丹	2024-06-21 16:19:01 +08:00
root	062ea5264a	使用encode方法，代码可读性更强	2024-06-21 16:08:39 +08:00
root	8ae10c60ff	原始代码的usertoken是针对2b的，其他模型会有问题,现在根据不同模型都会调整	2024-06-21 15:31:24 +08:00
Zhi Zheng	ab6b2d4346	Merge pull request #106 from cyx2000/add_model_settings ... fix: add fine-tuning model settings: bf16 and fp16 #92	2024-04-24 14:32:32 +08:00
Y.W. Fang	34ac3a2237	update readme and requirements about mlx	2024-04-11 14:22:03 +08:00
zR	6618dd93be	更新mlx 微调说明	2024-04-09 23:42:12 +08:00
zR	fdaab94f1e	更新训练集类型和推理fp16部分	2024-04-03 14:47:45 +08:00
zR	111657c02c	remove breakpoint	2024-03-27 23:17:50 +08:00
zR	5ab08cef50	update with finetune	2024-03-27 23:12:03 +08:00
winter	8ebe696889	add fine-tuning model settings: bf16 and fp16	2024-03-25 15:49:41 +08:00
Xiang Long	36337f70ea	Fix finetune supervised dataset issue	2024-03-16 01:58:08 +08:00
Xiang Long	74ecbcce5e	Fix sft_dataset issue and naming error	2024-03-06 17:25:41 +08:00
DingDing	4fb35907e6	Update README_en.md	2024-03-01 14:22:10 +08:00
DingDing	39bcb9b0e3	Update README_en.md	2024-03-01 14:21:43 +08:00
DingDing	a3e3095098	Update README.md	2024-03-01 14:20:40 +08:00
SillyXu	06df1992d2	Update README_en.md	2024-02-08 10:42:36 +09:00
SillyXu	bf80c52b96	Update README.md	2024-02-08 10:42:21 +09:00
SillyXu	c47f710b84	Update finetune.py	2024-02-08 10:41:37 +09:00
SillyXu	222ae66d3e	Update README_en.md	2024-02-08 10:36:43 +09:00
SillyXu	fbf5dea637	Update README.md	2024-02-08 10:36:17 +09:00
SillyXu	5647fa14b3	Update README_en.md	2024-02-01 13:59:03 +08:00
SillyXu	c3c5768f50	Update README_en.md	2024-02-01 13:58:43 +08:00
SillyXu	88df06f6b6	Update README.md	2024-02-01 13:58:13 +08:00
Xiang Long	9228c25f36	Add en version fine-tune README	2024-02-01 13:39:50 +08:00
Xiang Long	24a71e964f	Fix fine tune label offset bug	2024-02-01 12:51:30 +08:00
Xiang Long	213716ff0a	Fix SFT fine tune output dir and CUDA DEVICE NUM	2024-02-01 10:07:33 +08:00
Xiang Long	a250c200ed	Add README and update finetune scripts	2024-02-01 02:21:25 +08:00
Xiang Long	fb341897a6	Add fine tune scripts	2024-01-31 23:25:47 +08:00