cdpierse / cdpierse/transformers-interpret
Error :AssertionError: Forward hook did not obtain any outputs for given layer
- Dominant language
- Jupyter Notebook
- Stars
- 1.4k
- Forks
- 99
- PR merge metrics
- No merged PRs in 30d
Description
I was trying following code and found an error
from transformers import AutoModelForSequenceClassification, AutoTokenizer
from transformers_interpret import ZeroShotClassificationExplainer
tokenizer = AutoTokenizer.from_pretrained('facebook/bart-large-mnli')
model = AutoModelForSequenceClassification.from_pretrained('facebook/bart-large-mnli')
zero_shot_explainer = ZeroShotClassificationExplainer(model, tokenizer)
word_attributions = zero_shot_explainer(
"Today apple released the new Macbook showing off a range of new features found in the proprietary silicon chip computer. ",
labels = ["finance", "technology", "sports"],
)
AssertionError: Forward hook did not obtain any outputs for given layer
**Limitation: So your library cannot generate explanations for the outcomes generated by ''facebook/bart-large-mnli''??**
Contributor guide
Assessment
This issue has not been assessed yet.