SeifElden2342532/children_educational_summarizer

Summarization Model

This is a summarization model fine-tuned on a custom dataset. It is based on the allenai/led-base-16384 model.

Model Details

• Model type: Longformer-Encoder-Decoder (LED)
• Base model: allenai/led-base-16384
• Language: English
• License: apache-2.0

Training Data

The model was fine-tuned on a custom dataset for summarization. The dataset is a CSV file containing two columns: article and summary.

Training Procedure

The model was trained using the Hugging Face transformers library. The training script uses the Seq2SeqTrainer to fine-tune the model. The training arguments are as follows:

Argument	Value
num_train_epochs	3
per_device_train_batch_size	1
gradient_accumulation_steps	8
per_device_eval_batch_size	4
warmup_steps	500
weight_decay	0.01
logging_steps	5
eval_strategy	epoch
save_strategy	epoch
generation_max_length	256

How to Use

from transformers import AutoTokenizer, LEDForConditionalGeneration

model_name = "SeifElden2342532/children_educational_summarizer"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = LEDForConditionalGeneration.from_pretrained(model_name)

Text = "..."

inputs = tokenizer(Text, return_tensors="pt")

# Generate Summary
summary_ids = model.generate(inputs["input_ids"], num_beams=4, max_length=500, early_stopping=True)
summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)

print(summary)

Disclaimer

This model is part of the 3YNO project, an educational application targeting dyslexics and visual learners. It allows uploading a book/research/text content, then converting it into an explanatory video using artificial intelligence after extracting the scientific content from that content and converting it into a story or a narrative, then creating the characters.

GitHub Repository: https://github.com/SeifEldenOsama/3YNO/tree/main/models/model1(Summarizer)