Model Card for Model ID

Model Details

Model Description

This is a fine-tuned T5 model for text summarization using the SAMSum dataset. The model has been trained using ๐Ÿค— Transformers and Hugging Face Trainer with mixed precision (fp16) to optimize memory efficiency.

  • Developed by: Saravanan K
  • Finetuned from model [optional]: t5-base

Model Sources [optional]

Use Cases

Direct Use

This model can be used for text summarization tasks, particularly for summarizing dialogues and conversations.

Downstream Use

The model can be fine-tuned further on other summarization datasets or used in larger NLP applications requiring summarization capabilities.

Out Of Scope Use

The model may not perform well on non-dialogue-based text or non-English languages.

Bias, Risks, and Limitations

Biases: Since it is trained on the SAMSum dataset, it may have biases related to conversational English data. Limitations: Performance may degrade on texts that are significantly different from the training dataset.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

Define model name (same as uploaded one)

model_name = "Saravanankumaran/summarisation_model"

Load model and tokenizer from Hugging Face Hub

model = AutoModelForSeq2SeqLM.from_pretrained(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name)

print("Model loaded successfully! โœ…")

Below is the example text to use the model

text = """ Laxmi Kant: what work you planning to give Tom? Juli: i was hoping to send him on a business trip first. Laxmi Kant: cool. is there any suitable work for him? Juli: he did excellent in last quarter. i will assign new project, once he is back. """ inputs = tokenizer(text, return_tensors="pt")

output = model.generate(**inputs) summary = tokenizer.decode(output[0], skip_special_tokens=True)

print("Generated Output:", summary)

Downloads last month
33
Safetensors
Model size
223M params
Tensor type
F32
ยท
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.