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 phi3 mini 128k load error #5765

Merged
merged 2 commits into from
Jul 15, 2024
Merged

Fix phi3 mini 128k load error #5765

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cca0985
fix phi3 mini load error
Yejing-Lai Jul 11, 2024
bff5dd4
Merge branch 'master' into lyj/fix_phi3_mini
loadams Jul 11, 2024
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
2 changes: 1 addition & 1 deletion deepspeed/module_inject/auto_tp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ def is_load_module(module):
load_layer_names = [
"LPLayerNorm", "SharedEmbedding", "OPTLearnedPositionalEmbedding", "LlamaRMSNorm", "FalconLinear",
"MistralRMSNorm", "T5LayerNorm", "MixtralRMSNorm", "Phi3RotaryEmbedding", "Phi3SuScaledRotaryEmbedding",
"Phi3RMSNorm", "YuanRMSNorm", "YuanRotaryEmbedding"
"Phi3RMSNorm", "YuanRMSNorm", "YuanRotaryEmbedding", "Phi3LongRoPEScaledRotaryEmbedding"
]
return module.__class__ in load_layers or module._get_name() in load_layer_names

Expand Down
Loading