How can we use CPU offloading when using AutoModelForCausalLM and THUDM/cogvlm2-llama3-chat-19B #1246
nnilayyself-comment-ci.yml
on: issue_comment
Get PR number
Matrix: Run all tests for the model
Waiting for pending jobs
Update Check Run Status
Annotations
1 error
|
Invalid workflow file:
.github/workflows/self-comment-ci.yml#L10
The workflow is not valid. .github/workflows/self-comment-ci.yml (Line: 10, Col: 10): The maximum allowed memory size was exceeded while evaluating the following expression: format('{0}-{1}-{2}', github.workflow, github.event.issue.number, (startsWith(github.event.comment.body, 'run-slow') || startsWith(github.event.comment.body, 'run slow') || startsWith(github.event.comment.body, 'run_slow'))) .github/workflows/self-comment-ci.yml (Line: 10, Col: 10): Unexpected value ''
|