Model: Fix max_seq_len fallbacks

The rope alpha calculation caused an error if max seq len isn't
provided. This is because the model's max sequence length was not
stored as the target for alpha calculation.

Signed-off-by: kingbri <8082010+kingbri1@users.noreply.github.com>
This commit is contained in:
kingbri 2025-04-28 14:07:32 -04:00
parent 755f98a338
commit b43f0983c8

View file

@ -237,7 +237,8 @@ class ExllamaV2Container(BaseModelContainer):
base_seq_len = self.config.max_seq_len
# Set the target seq len if present
target_seq_len = kwargs.get("max_seq_len")
# Fallback to base_seq_len if not provided
target_seq_len = unwrap(kwargs.get("max_seq_len"), base_seq_len)
# Set the rope scale
self.config.scale_pos_emb = unwrap(