Conversation
|
Adding the "do-not-merge/release-note-label-needed" label because no release-note block was detected, please follow our release note process to remove it. DetailsInstructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository. |
|
[APPROVALNOTIFIER] This PR is NOT APPROVED This pull-request has been approved by: The full list of commands accepted by this bot can be found here. DetailsNeeds approval from an approver in each of these files:Approvers can indicate their approval by writing |
| from transformers import AutoModelForSequenceClassification, AutoTokenizer | ||
| self.model = model_name | ||
| self.cache_dir = cache_dir | ||
| self.model_kwargs = model_kwargs |
There was a problem hiding this comment.
The provided code checks out with no immediate errors or issues related to syntax, logic, or imports. The initialization of AutoModelForSequenceClassification and AutoTokenizer is correctly placed after the necessary libraries have been imported.
Optimization Suggestion: Ensure that the paths used in file operations (like reading data) are correct relative to where the script is being run, as this can lead to FileNotFoundError.
Additionally, consider handling exceptions such as when attempting to load models to avoid silent failures:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
class LocalReranker(MaxKBBaseModel, BaseDocumentCompressor):
__name__ = "LocalReranker"
def __init__(self, model_name : str, cache_dir: Optional[str] = None, **model_kwargs):
super().__init__()
try:
from transformers import AutoModelForSequenceClassification, AutoTokenizer
except ImportError as e:
raise SystemError(f"Failed to import required transformers library(s): {str(e)}")
self.model_name = model_name
self.cache_dir = cache_dir if cache_dir else "/path/to/default/cache/dir"
self.model_kwargs = model_kwargs
# Initialize or load the model hereThis modification adds basic error checking for missing dependencies and specifies a default path for caching models. Adjust the path according to how you set up your environment.
1 participant
fix: Rearrange model dependency