Downloads · 30 days
6
1% of all-time downloads
ZTamas/hubert-qa-milqa-impossible
hubert-qa-milqa-impossible is a question answering model from ZTamas. Use it when the input is a question plus a passage. It is set up for transformers.
This model is a fine-tuned version of mcsabai/huBert-fine-tuned-hungarian-squadv2 on the milqa dataset.
Downloads · 30 days
6
1% of all-time downloads
All-time downloads
900
Public
Repo size
880 MB
Likes
1
Public
Click a slice to open those files.
.bin440 MB · 100%
From the Hugging Face model README
This model is a fine-tuned version of mcsabai/huBert-fine-tuned-hungarian-squadv2 on the milqa dataset.
How to use:
from transformers import pipeline
qa_pipeline = pipeline(
"question-answering",
model = "ZTamas/hubert-qa-milqa-impossible",
tokenizer = "ZTamas/hubert-qa-milqa-impossible",
device = 0, #GPU selection, -1 on CPU
handle_impossible_answer = True,
max_answer_len = 50
)
predictions = qa_pipeline({
'context': context,
'question': question
})
print(predictions)