Intel
/

Qwen3-Coder-480B-A35B-Instruct-int4-mixed-AutoRound

4-bit precision

Model card Files Files and versions

wenhuach commited on Jul 24

Commit

51ecd16

·

verified ·

1 Parent(s): e772e91

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -49,8 +49,7 @@ inputs = tokenizer(texts, return_tensors="pt", padding=True, truncation=True, pa
 # conduct text completion
 outputs = model.generate(
     **inputs,
-    # max_new_tokens=65536, ## change to this to follow official usage
-    max_new_tokens=512
 )
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs["input_ids"], outputs)

 # conduct text completion
 outputs = model.generate(
     **inputs,
+    max_new_tokens=65536,
 )
 generated_ids = [
     output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs["input_ids"], outputs)