microsoft
/

Phi-4-mini-flash-reasoning

Text Generation

Model card Files Files and versions

renll commited on Jun 22, 2025

Commit

a892bba

·

verified ·

1 Parent(s): 47c33b0

Upload README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -151,7 +151,7 @@ inputs = tokenizer.apply_chat_template(
 outputs = model.generate(
     **inputs.to(model.device),
     max_new_tokens=32768,
-    temperature=0.8,
     top_p=0.95,
     do_sample=True,
 )

 outputs = model.generate(
     **inputs.to(model.device),
     max_new_tokens=32768,
+    temperature=0.6,
     top_p=0.95,
     do_sample=True,
 )