Skip to content

Fix pad token id issue for transformers v5 support #1058

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
vaibhavjindal merged 1 commit into from
Feb 3, 2026
Merged

Fix pad token id issue for transformers v5 support #1058

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
5 changes: 5 additions & 0 deletions test/transformers/test_monkey_patch.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -779,6 +779,7 @@ def test_apply_liger_kernel_to_instance_for_qwen3_vl_moe_for_conditional_generat
num_experts_per_tok=2,
num_experts=4,
mlp_only_layers=[],
pad_token_id=None,
).to_dict(),
)
dummy_model_instance = Qwen3VLMoeForConditionalGeneration._from_config(config)
Expand Down Expand Up @@ -884,6 +885,7 @@ def test_apply_liger_kernel_to_instance_for_qwen3_vl_moe():
num_experts_per_tok=2,
num_experts=4,
mlp_only_layers=[],
pad_token_id=None,
).to_dict(),
)
dummy_model_instance = Qwen3VLMoeModel._from_config(config)
Expand Down Expand Up @@ -965,6 +967,7 @@ def test_apply_liger_kernel_to_instance_for_qwen3_vl_moe_text():
num_experts_per_tok=2,
num_experts=4,
mlp_only_layers=[],
pad_token_id=None,
)
dummy_model_instance = Qwen3VLMoeTextModel._from_config(config)

Expand Down Expand Up @@ -1321,6 +1324,7 @@ def test_apply_liger_kernel_to_instance_for_llama4_for_conditional_generation():
num_hidden_layers=2,
vision_output_dim=64,
),
pad_token_id=None,
)
dummy_model_instance = Llama4ForConditionalGeneration._from_config(config)

Expand Down Expand Up @@ -2599,6 +2603,7 @@ def test_apply_liger_kernel_to_instance_for_glm4v():
"hidden_size": 32,
"intermediate_size": 64,
"hidden_act": "silu",
"pad_token_id": None,
},
vision_config={
"num_hidden_layers": 2,
Expand Down