-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
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
How to use Mamba2 like a RNN model? #622
Comments
YuBicheng
changed the title
How to use Mamba2 like a RNN
How to use Mamba2 like a RNN model?
Nov 15, 2024
I have the same idea. Have you solved it? |
1 similar comment
I have the same idea. Have you solved it? |
这个仓库的代码好像序列长度必须整除chunk大小,不然就报错 |
这个仓库的final_state 是RNN的Ht吗 |
这个仓库里面的step()函数会给出每一步的state,你可以理解为hidden state |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
In my task, the length of the input sequence is very long. During training, is it possible to get the hidden state of Mamba2, use it as a feature, and then feed the remaining input and hidden features into Mamba2 and continue the operation? Just like RNN
The text was updated successfully, but these errors were encountered: