github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-08-01 15:54:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse Source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2025-06-25 01:49:52 +00:00
parent bd8b57156b
commit a14bd0b411
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
colossalai/shardformer/policies/qwen2.py
View File

@ -308,7 +308,9 @@ class Qwen2Policy(Policy):
"self_attn.num_heads": self.model.config.num_attention_heads, "self_attn.num_heads": self.model.config.num_attention_heads,
} }
if getattr(self.model.config, "num_key_value_heads", False): if getattr(self.model.config, "num_key_value_heads", False):
decoder_attribute_replacement["self_attn.num_key_value_heads"] = self.model.config.num_key_value_heads decoder_attribute_replacement["self_attn.num_key_value_heads"] = (
self.model.config.num_key_value_heads
)
policy[Qwen2DecoderLayer] = ModulePolicyDescription(attribute_replacement=decoder_attribute_replacement) policy[Qwen2DecoderLayer] = ModulePolicyDescription(attribute_replacement=decoder_attribute_replacement)
self.append_or_create_method_replacement( self.append_or_create_method_replacement(