Skip to content
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

Re-Enable AdaptionPrompt when HuggingFace releases the PEFT fix. #3938

Closed
alexsherstinsky opened this issue Feb 21, 2024 · 0 comments
Closed
Assignees
Labels
llm Large Language Model related

Comments

@alexsherstinsky
Copy link
Collaborator

Describe the bug
On 02/21/2024, we had to disable AdaptionPrompt because of this error:

TypeError: LlamaRotaryEmbedding.forward() missing 1 required positional argument: 'position_ids')

which was traced to PEFT incompatibility.

To Reproduce
Steps to reproduce the behavior:

  1. Run pytest --cache-clear --full-trace -k "adaption_prompt-defaults" tests/integration_tests/test_llm.py::test_llm_finetuning_strategies -svv
  2. Run pytest --cache-clear --full-trace tests/integration_tests/test_llm.py::test_load_pretrained_adapter_weights -svv
  3. See errors

Please provide code, yaml config file and a sample of data in order to entirely reproduce the issue.
Issues that are not reproducible will be ignored.

Expected behavior
A clear and concise description of what you expected to happen.

Screenshots
If applicable, add screenshots to help explain your problem.

Environment (please complete the following information):

  • OS: [e.g. iOS]
  • Version [e.g. 22]
  • Python version
  • Ludwig version

Additional context
Add any other context about the problem here.

@alexsherstinsky alexsherstinsky self-assigned this Feb 21, 2024
@alexsherstinsky alexsherstinsky added the llm Large Language Model related label Jul 26, 2024
@mhabedank mhabedank closed this as not planned Won't fix, can't repro, duplicate, stale Oct 21, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
llm Large Language Model related
Projects
None yet
Development

No branches or pull requests

2 participants