neoneye/base64-encode-v1

Dataset: Base64 encode version1

This dataset is for improving base64 encoding capabilities.

GPT 4o is great at base64 encoding.

user: 
convert this hex data to base64:
880567a1

assistant:
The base64 encoding of the hex data `880567a1` is `iAVnoQ==`.

user:
convert this json data representing a byte sequence to base64:
[30,41,183]

assistant:
The base64 encoding of the JSON data `[30,41,183]` is `Him3`.

However llama3 is terrible at base64 encoding.

Short examples of what data.jsonl looks like:

{"instruction": "Encode hex to Base64", "input": "ecfc2db9ba6049165b", "output": "7PwtubpgSRZb"}
{"instruction": "change HEX to base64", "input": "60926e782008", "output": "YJJueCAI"}
{"instruction": "Json to base64", "input": "[77,62,160,64,248,233,105,133,5,248,89,239]", "output": "TT6gQPjpaYUF+Fnv"}
{"instruction": "Change Json to BASE64", "input": "[10,59,42,251,112,1]", "output": "Cjsq+3AB"}
{"instruction": "Convert JSON to Base64", "input": "[236,201,129,100,238]", "output": "7MmBZO4="}

Generate dataset

PROMPT> python generate_dataset.py

This creates the data.jsonl file.