Log inSign up
Problems / S10

Pack into JSON (chat) · SmolLM2 135M

400 ptschatsmollm2-135mCases 16max 16 tokensSet by dongbinna
Added October 11.

Statement

This is practically the same problem as Bundling into JSON (raw). This one is a chat mode problem.

InputAnswer you must give
이름: 김철수, 나이: 30{"name":"김철수","age":30}

When a model in the assistant state sees JSON, its habit of wrapping it in a backtick code block is very strong. That shape looks good when you show it to a person. The backticks count as characters too, so the moment it wraps the JSON the output differs from the expected value, and the habit of putting a space after the colon comes along with it.

Think about how to push that habit down.

Input

  • The input arrives as one line.

  • The input is always 15 characters long.

Output

  • Print one line of compact JSON on the first line.

  • The output is always 23 characters long.

  • Do not add any other characters.

  • Not a single character may differ from the expected value.

Requirements

  • The input is 이름: 홍길동, 나이: 25.
  • The output is one line of JSON with the spaces taken out.
  • This is chat mode. The prompt is wrapped in a chat template, so the model becomes an assistant. You can write control tokens yourself to build a conversation of several turns.
  • The output must match the expected value down to the last character. Only leading and trailing whitespace is ignored.
  • This problem is solved with SmolLM2 135M. It is a far smaller model than Qwen3 0.6B, so the same prompt does not simply carry over.
  • This model learned mostly from English, so it follows Korean instructions poorly. You may write your prompt in English. Only the input and the expected output have to stay as the problem defines them.
  • There are 16 cases, and 5 of them show the input together with the expected output. The rest show the input only.
  • Model output is accepted up to 16 tokens.
  • You have to pass all 16 cases to solve this.
Read the requirements carefully before solving. Gaming the score through prompt injection or similar tricks can get you sanctioned if caught.

Examples

The expected output for this problem is in Korean. The grader compares your output against Korean text, character for character. Look at the example cases below to see the exact words it expects. Your prompt itself can be written in English.

5 public cases. Judging also uses hidden cases. You have to pass all 16 cases to solve this.

Input
Expected output
이름: 김철수, 나이: 30
{"name":"김철수","age":30}
이름: 박영희, 나이: 27
{"name":"박영희","age":27}
이름: 이준호, 나이: 41
{"name":"이준호","age":41}
이름: 최민서, 나이: 19
{"name":"최민서","age":19}
이름: 정다은, 나이: 35
{"name":"정다은","age":35}

Notes

Background that helps with solving. The rules you have to follow are in the input and output specs and the requirements above.

SmolLM2 135M is a fraction of the size of Qwen3 0.6B. It lets instructions slide far more often. You have to say the same thing more briefly and more clearly for it to listen.

Among the lighter models some support Korean poorly, which makes certain problems hard to solve. You may use English in your prompt, so solve it as well as you can.

Prompt

SmolLM2 135M
Input to preview
This is the exact text that goes into the model (Sample input 1 is used here.)
This problem wraps your text in a chat template, so the exact text can only be shown once the model is loaded. Load SmolLM2 135M first with the button below.
0 chars
To solve problems you need to log in.