T5 Sentence To Triplet Xl

🚀 Peft

A fine-tuned version of flan-t5-xl for generating knowledge graph triplets from sentences.

🚀 Quick Start

This is a fine-tuned version of flan-t5-xl on the KELM Corpus. It takes sentences as input and outputs triplets in the form of subject-relation-object for knowledge graph generation.

✨ Features

• Uses custom tokens to delimit triplets.
• Fine-tuned on the KELM Corpus for knowledge graph triplet generation.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

The model uses custom tokens to delimit triplets:

special_tokens = ['<triplet>', '</triplet>', '<relation>', '<object>']
tokenizer.add_tokens(special_tokens)

You can use it like this:

model = model.to(device)
model.eval()

new_input = "Hugging Face, Inc. is an American company that develops tools for building applications using machine learning.",
inputs = tokenizer(new_input, return_tensors="pt")

with torch.no_grad():
    outputs = model.generate(input_ids=inputs["input_ids"].to("cuda"))
    print(tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=False)[0])

Output: <pad><triplet> Hugging Face <relation> instance of <object> Business </triplet></s>

🔧 Technical Details

This model still isn't perfect, and may make mistakes! The author is working on fine-tuning it for longer and on a more diverse set of data.

📄 License

This project is licensed under the Apache-2.0 license.