-
Notifications
You must be signed in to change notification settings - Fork 478
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Added fix for gpu support for other LLM attribution models #1307
Conversation
This pull request was exported from Phabricator. Differential Revision: D58897547 |
1 similar comment
This pull request was exported from Phabricator. Differential Revision: D58897547 |
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
This pull request was exported from Phabricator. Differential Revision: D58897547 |
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
21ded53
to
3f1c27e
Compare
This pull request was exported from Phabricator. Differential Revision: D58897547 |
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
3f1c27e
to
1b21e7a
Compare
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
This pull request was exported from Phabricator. Differential Revision: D58897547 |
1b21e7a
to
a3759e0
Compare
This pull request was exported from Phabricator. Differential Revision: D58897547 |
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
a3759e0
to
c247725
Compare
This pull request was exported from Phabricator. Differential Revision: D58897547 |
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
c247725
to
a498ec8
Compare
This pull request was exported from Phabricator. Differential Revision: D58897547 |
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
a498ec8
to
092d7a2
Compare
) Summary: Pull Request resolved: pytorch#1307 Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue. Reviewed By: cyrjano Differential Revision: D58897547
This pull request was exported from Phabricator. Differential Revision: D58897547 |
092d7a2
to
dd5051f
Compare
This pull request has been merged in 3125f59. |
Summary: Fixed bug in LLM Attribution code such that the attribution mask is on the same device as inputs. Followed post https://discuss.pytorch.org/t/trying-to-explain-zephyr-generative-llm/195262?fbclid=IwAR21fx6-IHV7QzW6FC3X2l8ol1pKBdTaDk9eRKOyXEXuyXk2tIxO_DDhE5A in order to fix the issue.
Reviewed By: cyrjano
Differential Revision: D58897547