microsoft
/

Phi-4-mini-reasoning

Text Generation

text-generation-inference

Model card Files Files and versions

garg-amit commited on Apr 29

Commit

7196d37

·

1 Parent(s): 661e722

fixed inf example

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -137,7 +137,7 @@ inputs = tokenizer.apply_chat_template(
     return_tensors="pt",
 )
-outputs = model.generate(**inputs.to(model.device), max_new_tokens=32768, num_logits_to_keep=1)
 outputs = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])
 print(outputs[0])

     return_tensors="pt",
 )
+outputs = model.generate(**inputs.to(model.device), max_new_tokens=32768)
 outputs = tokenizer.batch_decode(outputs[:, inputs["input_ids"].shape[-1]:])
 print(outputs[0])