Add paper ID to metadata

README.md

@@ -1,15 +1,16 @@
 ---
 base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+language:
+- en
 library_name: transformers
+license: apache-2.0
+paper: 2510.00492
 pipeline_tag: text-classification
 tags:
 - base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Llama-8B
 - lora
 - transformers
 - reward-model
-license: apache-2.0
-language:
-- en
 ---
 
 # dPRM-8B
@@ -40,7 +41,11 @@ candidate_tokens = [
   self.tokenizer.encode("-", add_special_tokens=False)[-1], 
   self.tokenizer.encode("+", add_special_tokens=False)[-1]
 ]
-tag_id = self.tokenizer.encode(" \n\n\n\n", add_special_tokens=False)[-1]
+tag_id = self.tokenizer.encode(" 
+
+
+
+", add_special_tokens=False)[-1]
 
 # model
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
@@ -48,13 +53,37 @@ model = AutoModelForCausalLM.from_pretrained('dongboklee/dPRM-8B')
 model.eval()
 model.to(device)
 
-question = 'Question: In Python 3, which of the following function convert a string to an int in python?\nA. short(x)\nB. float(x)\nC. integer(x [,base])\nD. double(x)\nE. int(x [,base])\nF. long(x [,base] )\nG. num(x)\nH. str(x)\nI. char(x)\nJ. digit(x [,base])'
+question = 'Question: In Python 3, which of the following function convert a string to an int in python?
+A. short(x)
+B. float(x)
+C. integer(x [,base])
+D. double(x)
+E. int(x [,base])
+F. long(x [,base] )
+G. num(x)
+H. str(x)
+I. char(x)
+J. digit(x [,base])'
 solution = ["To convert a string to an integer in Python 3, we use the built-in function int().",
             "The int() function takes two arguments: the string to be converted and an optional base (default is 10, which is for decimal).",
             "For example: int(\"123\", 10) converts the string \"123\" to the integer 123.",
             "Looking at the options, we can see that the correct function is option E: int(x [,base]).",
             "The answer is (E)."]
-input_text = question + ' \n\n' + ' \n\n\n\n'.join(solution) + ' \n\n\n\n' # solution steps are separated by ' \n\n\n\n'
+input_text = question + ' 
+
+' + ' 
+
+
+
+'.join(solution) + ' 
+
+
+
+' # solution steps are separated by ' 
+
+
+
+'
 input_id = torch.tensor([tokenizer.encode(input_text)]).to(device)
 
 with torch.no_grad():
@@ -73,4 +102,4 @@ with torch.no_grad():
   journal = {arXiv preprint arXiv:2510.00492},
   year    = {2025}
 }
-```
+```