Skip to content

[Model] Gemma 1.1 compatibility #2594

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 1 commit into from
Jun 19, 2024
Merged

[Model] Gemma 1.1 compatibility #2594

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
6 changes: 4 additions & 2 deletions python/mlc_llm/model/gemma/gemma_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ class GemmaConfig(ConfigBase): # pylint: disable=too-many-instance-attributes
"""Configuration of the Gemma model."""

hidden_size: int
hidden_act: str
hidden_activation: Optional[str]
intermediate_size: int
attention_bias: bool
num_attention_heads: int
Expand All @@ -39,7 +39,9 @@ class GemmaConfig(ConfigBase): # pylint: disable=too-many-instance-attributes
kwargs: Dict[str, Any] = dataclasses.field(default_factory=dict)

def __post_init__(self):
if self.hidden_act not in ("gelu", "gelu_pytorch_tanh"):
if self.hidden_activation is None:
self.hidden_activation = self.kwargs.get("hidden_act", None)
if self.hidden_activation not in ("gelu", "gelu_pytorch_tanh"):
raise ValueError("Only GeLU is supported as the activation for gemma.")
if self.attention_bias:
raise ValueError('Only "False" attention_bias is supported for gemma')
Expand Down