deepseekmirror/DeepSeek-Coder
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-Coder.git synced 2025-02-23 06:09:07 -05:00
Code Issues Actions Packages Projects Releases Wiki Activity

In the README.md the sample dataset format mentions 'instruction' and 'output' fields, but an example JSON line would be helpful.

Browse Source
This commit is contained in:
alexaustin007 2025-01-27 20:10:54 -05:00
parent b7ba565956
commit ec0774bc3e
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -282,6 +282,20 @@ pip install -r finetune/requirements.txt
Please follow [Sample Dataset Format](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) to prepare your training data. Please follow [Sample Dataset Format](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) to prepare your training data.
Each line is a json-serialized string with two required fields `instruction` and `output`. Each line is a json-serialized string with two required fields `instruction` and `output`.
Example of a JSON-serialized string, one formatted for use in Python and another for use in SQL.
###Python##
{
"instruction": "Write a Python function to calculate factorial",
"output": "def factorial(n):\n if n == 0:\n return 1\n else:\n return n * factorial(n-1)"
}
###SQL###
{
"instruction": "Create a SQL query to find duplicate emails",
"output": "SELECT email FROM users GROUP BY email HAVING COUNT(*) > 1;"
}
After data preparation, you can use the sample shell script to finetune `deepseek-ai/deepseek-coder-6.7b-instruct`. After data preparation, you can use the sample shell script to finetune `deepseek-ai/deepseek-coder-6.7b-instruct`.
Remember to specify `DATA_PATH`, `OUTPUT_PATH`. Remember to specify `DATA_PATH`, `OUTPUT_PATH`.