Skip to content

[mRope] Fix warnings #42660

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

Open
vasqu wants to merge 1 commit into
base: main
Choose a base branch
from
+20 −10
Open

[mRope] Fix warnings #42660

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
4 changes: 3 additions & 1 deletion src/transformers/models/glm4v/configuration_glm4v.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -234,7 +234,9 @@ def __init__(
self.attention_dropout = attention_dropout
self.rope_parameters = rope_parameters

super().__init__(tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope"}, **kwargs)
super().__init__(
tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope_section"}, **kwargs
)


class Glm4vConfig(PreTrainedConfig):
Expand Down
4 changes: 3 additions & 1 deletion src/transformers/models/glm4v/modular_glm4v.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -271,7 +271,9 @@ def __init__(
self.attention_dropout = attention_dropout
self.rope_parameters = rope_parameters

super().__init__(tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope"}, **kwargs)
super().__init__(
tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope_section"}, **kwargs
)


class Glm4vConfig(PreTrainedConfig):
Expand Down
4 changes: 3 additions & 1 deletion src/transformers/models/glm4v_moe/configuration_glm4v_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -280,7 +280,9 @@ def __init__(
self.first_k_dense_replace = first_k_dense_replace
self.norm_topk_prob = norm_topk_prob
self.router_aux_loss_coef = router_aux_loss_coef
super().__init__(tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope"}, **kwargs)
super().__init__(
tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope_section"}, **kwargs
)


class Glm4vMoeConfig(PreTrainedConfig):
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/glm4v_moe/modular_glm4v_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,7 @@ def __init__(
self.norm_topk_prob = norm_topk_prob
self.router_aux_loss_coef = router_aux_loss_coef
PreTrainedConfig.__init__(
self, tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope"}, **kwargs
self, tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope_section"}, **kwargs
)


Expand Down
6 changes: 4 additions & 2 deletions src/transformers/models/qwen2_5_omni/configuration_qwen2_5_omni.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -365,7 +365,7 @@ def __init__(
self.rope_parameters = rope_parameters
super().__init__(
tie_word_embeddings=tie_word_embeddings,
ignore_keys_at_rope_validation={"mrope"},
ignore_keys_at_rope_validation={"mrope_section"},
**kwargs,
)

Expand Down Expand Up @@ -713,7 +713,9 @@ def __init__(
layer_type_validation(self.layer_types, self.num_hidden_layers)

self.rope_parameters = rope_parameters
super().__init__(tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope"}, **kwargs)
super().__init__(
tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope_section"}, **kwargs
)


class Qwen2_5OmniDiTConfig(PreTrainedConfig):
Expand Down
6 changes: 4 additions & 2 deletions src/transformers/models/qwen2_5_omni/modular_qwen2_5_omni.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -399,7 +399,7 @@ def __init__(
self.rope_parameters = rope_parameters
super().__init__(
tie_word_embeddings=tie_word_embeddings,
ignore_keys_at_rope_validation={"mrope"},
ignore_keys_at_rope_validation={"mrope_section"},
**kwargs,
)

Expand Down Expand Up @@ -747,7 +747,9 @@ def __init__(
layer_type_validation(self.layer_types, self.num_hidden_layers)

self.rope_parameters = rope_parameters
super().__init__(tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope"}, **kwargs)
super().__init__(
tie_word_embeddings=tie_word_embeddings, ignore_keys_at_rope_validation={"mrope_section"}, **kwargs
)


class Qwen2_5OmniDiTConfig(PreTrainedConfig):
Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/qwen2_5_vl/configuration_qwen2_5_vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -230,7 +230,7 @@ def __init__(
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
pad_token_id=pad_token_id,
ignore_keys_at_rope_validation={"mrope"},
ignore_keys_at_rope_validation={"mrope_section"},
**kwargs,
)

Expand Down
2 changes: 1 addition & 1 deletion src/transformers/models/qwen2_vl/configuration_qwen2_vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -218,7 +218,7 @@ def __init__(
bos_token_id=bos_token_id,
eos_token_id=eos_token_id,
pad_token_id=pad_token_id,
ignore_keys_at_rope_validation={"mrope"},
ignore_keys_at_rope_validation={"mrope_section"},
**kwargs,
)

Expand Down