Skip to content
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

Fix typo of Block. #28727

Merged
merged 1 commit into from
Jan 29, 2024
Merged

Fix typo of Block. #28727

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
12 changes: 10 additions & 2 deletions src/transformers/models/mixtral/modeling_mixtral.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -787,7 +787,7 @@ def forward(
}


class MixtralBLockSparseTop2MLP(nn.Module):
class MixtralBlockSparseTop2MLP(nn.Module):
def __init__(self, config: MixtralConfig):
super().__init__()
self.ffn_dim = config.intermediate_size
Expand All @@ -805,6 +805,14 @@ def forward(self, hidden_states):
return current_hidden_states


class MixtralBLockSparseTop2MLP(MixtralBlockSparseTop2MLP):
def __init__(self, *args, **kwargs):
logger.warning_once(
"MixtralBLockSparseTop2MLP is deprecated by MixtralBlockSparseTop2MLP and will be removed in v4.40."
)
super().__init__(*args, **kwargs)


class MixtralSparseMoeBlock(nn.Module):
"""
This implementation is
Expand All @@ -827,7 +835,7 @@ def __init__(self, config):
# gating
self.gate = nn.Linear(self.hidden_dim, self.num_experts, bias=False)

self.experts = nn.ModuleList([MixtralBLockSparseTop2MLP(config) for _ in range(self.num_experts)])
self.experts = nn.ModuleList([MixtralBlockSparseTop2MLP(config) for _ in range(self.num_experts)])

def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
""" """
Expand Down
Loading