Skip to content

Update more modular examples #44834

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
Cyrilvallez merged 1 commit into from
Mar 18, 2026
Merged

Update more modular examples #44834

Show file tree
Hide file tree
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
1 change: 0 additions & 1 deletion examples/modular-transformers/configuration_new_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,6 @@ class NewModelConfig(PreTrainedConfig):
"layers": (["hidden_states", "attention_mask"], ["hidden_states"]),
"norm": (["hidden_states"], ["hidden_states"]),
}

vocab_size: int = 256030
hidden_size: int = 64
intermediate_size: int = 90
Expand Down
1 change: 0 additions & 1 deletion examples/modular-transformers/modeling_dummy_bert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -556,7 +556,6 @@ def forward(
output_attentions: bool | None = None,
output_hidden_states: bool | None = None,
return_dict: bool | None = None,
cache_position: torch.Tensor | None = None,
**kwargs: Unpack[TransformersKwargs],
) -> tuple[torch.Tensor] | BaseModelOutputWithPoolingAndCrossAttentions:
if (input_ids is None) ^ (inputs_embeds is not None):
Expand Down
2 changes: 0 additions & 2 deletions examples/modular-transformers/modeling_new_task_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,7 +420,6 @@ def forward(
position_ids: torch.LongTensor | None = None,
past_key_values: Cache | None = None,
token_type_ids: torch.LongTensor | None = None,
cache_position: torch.LongTensor | None = None,
inputs_embeds: torch.FloatTensor | None = None,
labels: torch.LongTensor | None = None,
use_cache: bool | None = None,
Expand All @@ -439,7 +438,6 @@ def forward(
position_ids=position_ids,
past_key_values=past_key_values,
token_type_ids=token_type_ids,
cache_position=cache_position,
inputs_embeds=inputs_embeds,
labels=labels,
use_cache=use_cache,
Expand Down
2 changes: 0 additions & 2 deletions examples/modular-transformers/modeling_super.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -359,7 +359,6 @@ def forward(
output_attentions: bool | None = None,
output_hidden_states: bool | None = None,
return_dict: bool | None = None,
cache_position: torch.LongTensor | None = None,
) -> tuple | CausalLMOutputWithPast:
out = super().forward(
input_ids,
Expand All @@ -371,7 +370,6 @@ def forward(
output_attentions,
output_hidden_states,
return_dict,
cache_position,
)
out.logits *= 2**4
return out
1 change: 0 additions & 1 deletion examples/modular-transformers/modular_dummy_bert.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,6 @@ def forward(
output_attentions: bool | None = None,
output_hidden_states: bool | None = None,
return_dict: bool | None = None,
cache_position: torch.Tensor | None = None,
**kwargs: Unpack[TransformersKwargs],
) -> tuple[torch.Tensor] | BaseModelOutputWithPoolingAndCrossAttentions:
return super().forward(input_ids, **kwargs)
2 changes: 0 additions & 2 deletions examples/modular-transformers/modular_new_task_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,6 @@ def forward(
position_ids: torch.LongTensor | None = None,
past_key_values: Cache | None = None,
token_type_ids: torch.LongTensor | None = None,
cache_position: torch.LongTensor | None = None,
inputs_embeds: torch.FloatTensor | None = None,
labels: torch.LongTensor | None = None,
use_cache: bool | None = None,
Expand All @@ -47,7 +46,6 @@ def forward(
position_ids=position_ids,
past_key_values=past_key_values,
token_type_ids=token_type_ids,
cache_position=cache_position,
inputs_embeds=inputs_embeds,
labels=labels,
use_cache=use_cache,
Expand Down
2 changes: 0 additions & 2 deletions examples/modular-transformers/modular_super.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ def forward(
output_attentions: bool | None = None,
output_hidden_states: bool | None = None,
return_dict: bool | None = None,
cache_position: torch.LongTensor | None = None,
) -> tuple | CausalLMOutputWithPast:
out = super().forward(
input_ids,
Expand All @@ -31,7 +30,6 @@ def forward(
output_attentions,
output_hidden_states,
return_dict,
cache_position,
)
out.logits *= 2**4
return out
Loading