Skip to content

GitLab

Unverified Commit f4dc26d4 authored by Joao Gante's avatar Joao Gante Committed by GitHub
Browse files

Qwen: incorrect setup flag (#30776) 

qwen does not support the new cache classes
parent f823fec5
Show whitespace changes
Inline Side-by-side
Showing with 0 additions and 1 deletion
src/transformers/models/qwen2/modeling_qwen2.py
View file @ f4dc26d4
...@@ -821,7 +821,6 @@ class Qwen2PreTrainedModel(PreTrainedModel): ...@@ -821,7 +821,6 @@ class Qwen2PreTrainedModel(PreTrainedModel):
_skip_keys_device_placement = "past_key_values" _skip_keys_device_placement = "past_key_values"
_supports_flash_attn_2 = True _supports_flash_attn_2 = True
_supports_sdpa = True _supports_sdpa = True
_supports_cache_class = True
def _init_weights(self, module): def _init_weights(self, module):
std = self.config.initializer_range std = self.config.initializer_range
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment