Qwen: incorrect setup flag (#30776)

qwen does not support the new cache classes

Qwen: incorrect setup flag (#30776)
qwen does not support the new cache classes
f4dc26d4 · Joao Gante · GitHub · f823fec5 · f4dc26d4
Unverified Commit f4dc26d4 authored May 13, 2024 by Joao Gante Committed by GitHub May 13, 2024
Hide whitespace changes
Inline Side-by-side

Showing with 0 additions and 1 deletion

src/transformers/models/qwen2/modeling_qwen2.py src/transformers/models/qwen2/modeling_qwen2.py +0 -1

No files found.
--- a/src/transformers/models/qwen2/modeling_qwen2.py
+++ b/src/transformers/models/qwen2/modeling_qwen2.py
@@ -821,7 +821,6 @@ class Qwen2PreTrainedModel(PreTrainedModel):
    _skip_keys_device_placement = "past_key_values"
    _supports_flash_attn_2 = True
    _supports_sdpa = True
-    _supports_cache_class = True

    def _init_weights(self, module):
        std = self.config.initializer_range