You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
How does StarCoder-15b generates concept, instruction, and responses? #14
Thank you for getting back to me. I saw the code. Given a code snippet, isn't it hard to generate concepts/instructions for a base model? I saw the code and realized the prompt was quite simple and straight-forward. Did you evaluate how well the base model in generating concepts/instructions? Any analysis or findings from earlier experiments?
You can find the instructions from an earlier selfcodealign, starcoder2-instruct. Sorry the instructions for the new version has not been updated yet. It's mostly compatible with the old one, but we will release an updated README soon.
Regarding the analysis, the section 4.1 (Self-Alignment with Different Models) in our paper might be of your interest.
Activity
UniverseFly commentedon Nov 5, 2024
Hi, StarCoder-15b is a base model, and we use it to generate data and create starcoder2-instruct. The main pipeline code is here: https://github.com/bigcode-project/selfcodealign/blob/46749cceeb84cf1773deb5c157b04930acebc5cd/src/star_align/self_ossinstruct.py.
wasiahmad commentedon Nov 5, 2024
Thank you for getting back to me. I saw the code. Given a code snippet, isn't it hard to generate concepts/instructions for a base model? I saw the code and realized the prompt was quite simple and straight-forward. Did you evaluate how well the base model in generating concepts/instructions? Any analysis or findings from earlier experiments?
UniverseFly commentedon Nov 6, 2024
You can find the instructions from an earlier selfcodealign, starcoder2-instruct. Sorry the instructions for the new version has not been updated yet. It's mostly compatible with the old one, but we will release an updated README soon.
Regarding the analysis, the section 4.1 (Self-Alignment with Different Models) in our paper might be of your interest.