Question Answering
Transformers
Safetensors
English
doge
text-generation
trl
sft
grpo
custom_code
JingzeShi commited on
Commit
3386f14
verified
1 Parent(s): 3091cae

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -63,7 +63,8 @@ Your role as an assistant involves thoroughly exploring questions through a syst
63
  """.strip()
64
  prompt = "Which number is bigger, 3.9 or 3.11?"
65
  conversation = [
66
- {"role": "user", "content": prompt}
 
67
  ]
68
  inputs = tokenizer.apply_chat_template(
69
  conversation=conversation,
 
63
  """.strip()
64
  prompt = "Which number is bigger, 3.9 or 3.11?"
65
  conversation = [
66
+ {"role": "system", "content": system_prompt},
67
+ {"role": "user", "content": prompt}
68
  ]
69
  inputs = tokenizer.apply_chat_template(
70
  conversation=conversation,