microsoft / microsoft/LLMLingua

[Bug]: XLMRobertaForTokenClassification.forward() got an unexpected keyword argument 'past_key_values'

Open
#232 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
6.7k
Forks
428
Avg merge
2d 4h
Merged PRs (30d)
1

Description

Describe the bug

When I strictly followed the instructions in the README and attempted to execute SecurityLingu using the weights you provided on huggingface, I encountered the following two errors successively. To solve the first error, I deleted "use_slingua", and then encountered the second error. I think there is some bug in this.

TypeError: PromptCompressor.init() got an unexpected keyword argument 'use_slingua'
XLMRobertaForTokenClassification.forward() got an unexpected keyword argument 'past_key_values'

Steps to reproduce

No response

Expected Behavior

No response

Logs

No response

Additional Information

No response

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the README instructions for running SecurityLingu and trace PromptCompressor initialization, including the use_slingua argument. Then reproduce the second error with the provided Hugging Face weights and follow the call into XLMRobertaForTokenClassification.forward(). Done means both reported TypeErrors are resolved or the required compatible versions and usage are documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.