Skip to content

Commit 34279f2

Browse files
Update generative-proof-of-concept-CPU-preprocessing-in-memory.py
Correct variable nomenclature.
1 parent 7b82030 commit 34279f2

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

generative-proof-of-concept-CPU-preprocessing-in-memory.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -794,7 +794,7 @@ def generate(self, token_ids, do_sample=False, max_new_tokens=None, temperature=
794794

795795
for _ in range(max_new_tokens):
796796
# (padding code as existing)
797-
input_tensor = tf.constant([input_tokens], dtype=tf.int32)
797+
input_tensor = tf.constant([token_ids], dtype=tf.int32)
798798
logits = self.model(input_tensor)
799799

800800
# Apply temperature scaling (logits->probs because your model returns softmax)

0 commit comments

Comments
 (0)