Pragmaticlm

🚀 PragmaticLM - T5 for Prompt Restructuring

PragmaticLM is a fine - tuned T5 model. It aims to restructure and reframe user prompts, making them easier for downstream LLMs to understand. By using contextual restructuring techniques, the model enhances the clarity of prompts.

🚀 Quick Start

Basic Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

tokenizer = AutoTokenizer.from_pretrained("aliMohammad16/pragmaticLM")
model = AutoModelForSeq2SeqLM.from_pretrained("aliMohammad16/pragmaticLM")

def restructure_prompt(input_prompt):
    input_text = f"Restructure Prompt: {input_prompt}"
    inputs = tokenizer(input_text, return_tensors="pt", padding=True)
    
    output = model.generate(
        inputs.input_ids,
        max_length=64,
        num_beams=4,
        early_stopping=True
    )
    
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Example Usage
test_prompt = "I am not feeeling well. I need to consult a doctor nearby."
print(restructure_prompt(test_prompt))

✨ Features

PragmaticLM is designed to restructure and reframe user prompts, enhancing prompt clarity through contextual restructuring techniques for better understanding by downstream LLMs.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

📚 Documentation

📌 Overview

PragmaticLM is a fine - tuned T5 model designed to restructure and reframe user prompts for better understanding by downstream LLMs. The model enhances prompt clarity by leveraging contextual restructuring techniques.

🚀 Model Details

📊 Training Configuration

• Epochs: 10
• Batch Size: 8
• Learning Rate: Encoder: 1e - 5, Decoder: 3e - 5
• Optimizer: AdamW
• Loss Function: Cross - entropy loss
• Hardware: GPU (T4)

⏳ Improvements

• Work in progress: This is a work in progress. I am actively working on this model.
• Update: Next I am implementing a multimodular pipeline, integrating TinyLlama 1.1B and Llama Index RAG with prompt - restructuring model, to improve output generation.

📄 License

The model is licensed under the Apache 2.0 license.