Skip to content

fix: no need to dtype A in jamba #32924

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.

Sign up for GitHub

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

Merged
merged 1 commit into from
Aug 22, 2024
Merged

fix: no need to dtype A in jamba #32924

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/transformers/models/jamba/modeling_jamba.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -630,7 +630,7 @@ def __init__(self, config: JambaConfig, layer_idx):

# S4D real initialization. These are not discretized!
# The core is to load them, compute the discrete states, then write the updated state. Keeps the memory bounded
A = torch.arange(1, self.ssm_state_size + 1, dtype=torch.float32)[None, :]
A = torch.arange(1, self.ssm_state_size + 1)[None, :]
A = A.expand(self.intermediate_size, -1).contiguous()

self.A_log = nn.Parameter(torch.log(A))
Expand Down