We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
你好,想问下one-DM在训练阶段,是整个模型从头开始训练还是基于其他模型进行finetune呢,论文里提到使用4张3090的卡进行训练,想问下你们一共训练了多久
The text was updated successfully, but these errors were encountered:
我们是从头开始预训练的。4张3090大概需要三天左右。
Sorry, something went wrong.
想问下,论文里有放出中文的测试效果,这个结果是用基于中文训练集训练出来的模型推理得到的吗
还有想问下,训练数据这里想请教下是怎么进行处理呢,如果要在中文数据集上训练的话,有处理好的数据集可以使用吗
是的,在中科院自动化所发布的CASIA中文数据集上进行训练的
No branches or pull requests
你好,想问下one-DM在训练阶段,是整个模型从头开始训练还是基于其他模型进行finetune呢,论文里提到使用4张3090的卡进行训练,想问下你们一共训练了多久
The text was updated successfully, but these errors were encountered: