nvidia
/

AceMath-RL-Nemotron-7B

Text Generation

reinforcement learning

text-generation-inference

Model card Files Files and versions Community

zihanliu commited on about 22 hours ago

Commit

2099899

·

verified ·

1 Parent(s): 009977d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -80,7 +80,7 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ## Usage Recommendations
 1. Don't include a system prompt; instead, place all instructions directly in the user prompt.
-2. We recommend using the following prompt format for math questions:<br>*<｜begin▁of▁sentence｜><｜User｜>{math_question}\nPlease reason step by step, and put your final answer within \boxed{}.<｜Assistant｜><think>\n*
 ## Correspondence to

 ## Usage Recommendations
 1. Don't include a system prompt; instead, place all instructions directly in the user prompt.
+2. We recommend using the following prompt format for math questions:<br>*<｜begin▁of▁sentence｜><｜User｜>{math_question}\nPlease reason step by step, and put your final answer within \boxed{}.<｜Assistant｜>\<think\>\n*
 ## Correspondence to