Skip to content

[misc] fix typos #5872

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
Hz188 merged 1 commit into from
Jul 1, 2024
Merged

[misc] fix typos #5872

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
8 changes: 4 additions & 4 deletions colossalai/shardformer/policies/deepseek.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,11 +39,11 @@ def module_policy(self) -> Dict[Union[str, nn.Module], ModulePolicyDescription]:
if self.shard_config.enable_sequence_parallelism:
self.shard_config.enable_sequence_parallelism = False
raise NotImplementedError(
"Mixtral dosen't support sequence parallelism now, will ignore the sequence parallelism flag."
"Deepseek dosen't support sequence parallelism now, will ignore the sequence parallelism flag."
)

if self.shard_config.enable_tensor_parallelism:
raise NotImplementedError("Tensor parallelism is not supported for Mixtral model now.")
raise NotImplementedError("Tensor parallelism is not supported for Deepseek model now.")
if getattr(self.shard_config, "ep_group", None) is None:
raise ValueError("You must pass in ep_group via shard_config for expert parallel!")

Expand Down Expand Up @@ -117,7 +117,7 @@ def get_held_layers(self) -> List[Module]:
"""Get pipeline layers for current stage."""
assert self.pipeline_stage_manager is not None

if self.model.__class__.__name__ == "MixtralModel":
if self.model.__class__.__name__ == "DeepseekModel":
module = self.model
else:
module = self.model.model
Expand Down Expand Up @@ -145,7 +145,7 @@ def module_policy(self):
# set None as default
self.set_pipeline_forward(
model_cls=DeepseekModel,
new_forward=DeepseekPipelineForwards.mixtral_model_forward,
new_forward=DeepseekPipelineForwards.deepseek_model_forward,
policy=policy,
)
return policy
Expand Down