Skip to content

Fix errors when use verl to train GLM4.1v model #39199

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 2 commits into from
Jul 8, 2025
Merged

Fix errors when use verl to train GLM4.1v model #39199

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
2a3f55b
Fix errors when use verl to train GLM4.1v model
kaln27 Jul 3, 2025
f06fa5c
Update modeling_auto.py
kaln27 Jul 8, 2025
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: 2 additions & 2 deletions src/transformers/models/glm4v/modeling_glm4v.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -949,7 +949,7 @@ def forward(
@auto_docstring
class Glm4vModel(Glm4vPreTrainedModel):
base_model_prefix = ""
_checkpoint_conversion_mapping = None
_checkpoint_conversion_mapping = {}
config_class = Glm4vConfig
_no_split_modules = ["Glm4vTextDecoderLayer", "Glm4vVisionBlock"]

Expand Down Expand Up @@ -1382,7 +1382,7 @@ class Glm4vCausalLMOutputWithPast(ModelOutput):


class Glm4vForConditionalGeneration(Glm4vPreTrainedModel, GenerationMixin):
_checkpoint_conversion_mapping = None
_checkpoint_conversion_mapping = {}
_tied_weights_keys = ["lm_head.weight"]

def __init__(self, config):
Expand Down
4 changes: 2 additions & 2 deletions src/transformers/models/glm4v/modular_glm4v.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1001,7 +1001,7 @@ def forward(


class Glm4vModel(Qwen2_5_VLModel):
_checkpoint_conversion_mapping = None
_checkpoint_conversion_mapping = {}
_no_split_modules = ["Glm4vTextDecoderLayer", "Glm4vVisionBlock"]

def __init__(self, config):
Expand Down Expand Up @@ -1356,7 +1356,7 @@ class Glm4vCausalLMOutputWithPast(Qwen2_5_VLCausalLMOutputWithPast):


class Glm4vForConditionalGeneration(Qwen2_5_VLForConditionalGeneration):
_checkpoint_conversion_mapping = None
_checkpoint_conversion_mapping = {}

def forward(
self,
Expand Down