gaotang
/

RM-R1-DeepSeek-Distilled-Qwen-7B

Text Generation

text-generation-inference

Model card Files Files and versions

gaotang commited on Jun 28

Commit

ba9ac5e

·

verified ·

1 Parent(s): 440ff6e

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -89,7 +89,7 @@ input_ids = tokenizer.apply_chat_template(
 generation = model.generate(
     input_ids=input_ids,
-    max_new_tokens=8192,
     do_sample=False,
 )

 generation = model.generate(
     input_ids=input_ids,
+    max_new_tokens=8192,  # For optimal performance benchmarking, please set this to unlimited (e.g., 50000)
     do_sample=False,
 )