Downloads · 30 days
8
30% of all-time downloads
Hard_QG_Generator
goenkalokesh/Hard_QG_Generator
Hard_QG_Generator is a machine learning model from goenkalokesh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
All-time downloads
27
Public
Parameters
223M
892 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors892 MB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- t5
- Access
- Public
- Created
- Jun 18, 2024
- Updated
- Jul 4, 2024
- SHA
- 0d519245
Model card
From the Hugging Face model README
Model Card for Hard_QG_Generator
Model Details
Model Name: Hard_QG_Generator
Model Description: This model can generate MCQs from a given passage.
Model Type: Transformer.
License: Acache-2.0
Author: Lokesh Goenka
Intended Use Primary Use Cases: Generating MCQs from a given Passage. Generate MCQ-based tests for kids
Primary Users: Teachers, Students, Researchers.
Limitations and Risks Limitations: Limitation in the number of generated questions.
Training Data Data Sources:
NCERT Books https://epathshala.nic.in//process.php?id=students&type=eTextbooks&ln=en#content
Usage Example Usage:
Python hard_model = T5ForConditionalGeneration.from_pretrained("goenkalokesh/Hard_QG_Generator")
hard_tokenizer = T5Tokenizer.from_pretrained("goenkalokesh/Hard_QG_Generator")
prompt ='''Your Prompt'''
input_text = f"{prompt}: {passage.strip()}"
input_ids = hard_tokenizer.encode(input_text, return_tensors='pt')
outputs = hard_model.generate(
input_ids,
max_length=max_length,
num_beams=num_beams,
early_stopping=early_stopping,
no_repeat_ngram_size=3
)
output_text = hard_tokenizer.decode(outputs[0], skip_special_tokens=True)
print(output_text)
- Library
- transformers
- Type
- t5
- License
- apache-2.0
- Languages
- en
- Created
- Jun 18, 2024
- Updated
- Jul 4, 2024