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

Add position_ids argument to DistributedFalconModel #525

Merged
merged 1 commit into from
Oct 8, 2023
Merged

Add position_ids argument to DistributedFalconModel #525

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
4 changes: 4 additions & 0 deletions src/petals/models/falcon/model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ def forward(
input_ids: Optional[torch.LongTensor] = None,
past_key_values: Optional[RemotePastKeyValues] = None,
attention_mask: Optional[torch.Tensor] = None,
position_ids: Optional[torch.LongTensor] = None,
head_mask: Optional[torch.LongTensor] = None,
inputs_embeds: Optional[torch.LongTensor] = None,
use_cache: Optional[bool] = None,
Expand All @@ -68,6 +69,9 @@ def forward(
assert (
attention_mask is None or (attention_mask == 1).all()
), f"Custom attention masks are not supported, {attention_mask=}"
assert (
position_ids is None or (position_ids[:, 1:] - position_ids[:, :-1] == 1).all()
), f"Non-consecutive position_ids are not supported, {position_ids=}"
assert head_mask is None, f"Custom head masks are not supported, {head_mask=}"
assert use_cache is None or use_cache, f"{use_cache=} is not supported"
assert not output_attentions, f"{output_attentions=} is not supported"
Expand Down
Loading