You can deploy this model and start earning money today!

ambrosfitz/
summarize-grammar

Name: summarize-grammar
Availability: InStock

safetensors

summarization

grammar-enhanced

ambrosfitz/grammar-summary

apache-2.0

model-index

Views

No views yet

Grammar-Enhanced T5 Summarizer

This model is a fine-tuned version of T5-base for text summarization with grammar-enhanced inputs. It was trained on historical text summaries with explicit grammar structure analysis.

Model Description

Base Model: T5-base
Task: Text Summarization
Training Data: Historical texts with grammar analysis
Input Format: Structured text with grammar analysis (subjects, verbs, objects, relationships)
Output Format: Concise summary

Usage

python

from transformers import T5ForConditionalGeneration, T5Tokenizer

# Load model and tokenizer
model = T5ForConditionalGeneration.from_pretrained("ambrosfitz/summarize-grammar")
tokenizer = T5Tokenizer.from_pretrained("ambrosfitz/summarize-grammar")

# Prepare input
text = "Your text here..."
input_text = f"summarize: {text}"

# Generate summary
inputs = tokenizer(input_text, return_tensors="pt", max_length=512, truncation=True)
outputs = model.generate(**inputs, max_length=150, num_beams=4, length_penalty=2.0)
summary = tokenizer.decode(outputs[0], skip_special_tokens=True)

Training Details

The model was fine-tuned on a dataset of historical texts with additional grammar analysis information. Each input includes:

Main subjects
Key verbs
Objects
Grammatical relationships

The model achieved a validation loss of 0.8700 during training.

Limitations

This model works best with:

Historical texts
Formal writing
English language content
Texts that benefit from structural analysis

Citation

If you use this model, please cite:

@misc{grammar-t5-summarizer,
  author = {repo_owner},
  title = {Grammar-Enhanced T5 Summarizer},
  year = {2024},
  publisher = {Hugging Face},
  journal = {Hugging Face Model Hub},
  howpublished = {https://huggingface.co/ambrosfitz/summarize-grammar}
}