Skip to content
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

Audio Encoder to bfloat16 #4

Merged
merged 2 commits into from
Jun 3, 2024
Merged

Audio Encoder to bfloat16 #4

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7d880f6
audio enc to bfloat16
farzadab Jun 3, 2024
d4417f4
increase transformers min required version
farzadab Jun 3, 2024
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 requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# Core
transformers[torch]>=4.39.3
transformers[torch]>=4.40.2
bitsandbytes>=0.42.0
peft
simple_parsing
Expand Down
4 changes: 1 addition & 3 deletions ultravox/training/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -174,9 +174,7 @@ def main() -> None:
logging.info(
f"Using dtype and device (world_size): {dtype}, {device} ({world_size})"
)
model.to(device)
model.language_model.to(dtype)
model.multi_modal_projector.to(dtype)
model.to(device=device, dtype=dtype)
# TODO: check if the whole model can now be moved to dtype instead

# Prepare dataset, subsetting if needed
Expand Down
Loading