Generative and Large Language Models

This repository contains various projects and experiments related to generative and large language models (LLMs). It includes implementations, fine-tuning techniques, and deployment strategies for state-of-the-art models.

Repository Structure

• LLM_Finetuning/: Contains notebooks and scripts for fine-tuning large language models, including instruction-based fine-tuning and parameter-efficient fine-tuning (PEFT).

  • Generative_AI_Finetuning.ipynb: Notebook for generative AI and LLM fine-tuning.

• dialogue-summary-training-1723532164/: Checkpoints and logs for dialogue summarization training runs.

  • Aug13_06-56-04_c7eabaa1b850/: Training run data.

• instruct_model/: Training artifacts for instruction-based models.

  • training_args.bin: Configuration file for the instruct model.

• peft-dialogue-summary-checkpoint-local/: Checkpoints for dialogue summarization using PEFT.

  • checkpoint files: Model checkpoints.

• Human-Centric Dialogue Summarization.ipynb: Notebook demonstrating the development of a human-centric dialogue summarization model, including fine-tuning and performance metrics.

• Object_Detection(Pytorch).ipynb: Notebook for object detection using PyTorch.

• Sentimental_Analysis.py: Script for sentiment analysis on IMDB reviews using vanilla RNN.

• Streamlit_Deployment.ipynb: Notebook for deploying models using Streamlit.

• README.md: This file.

Key Features

• LLM Fine-Tuning: Techniques for fine-tuning large language models, including instruction-based methods and PEFT.
• Human-Centric Summarization: Implementations for generating human-like summaries using advanced LLMs.
• Object Detection: PyTorch-based object detection models.
• Sentiment Analysis: RNN-based sentiment analysis on IMDB reviews.
• Streamlit Deployment: Guides and examples for deploying models with Streamlit.

Getting Started

1. Clone the Repository:

   git clone https://github.com/SahilBarbade1203/Neural_Networks_and_Large_Language_Models.git

2. **Navigate to the Desired Directory:

   cd Neural_Networks_and_Large_Language_Models

3. **Install Dependencies: Ensure you have the necessary dependencies installed. You can use a requirements.txt or install them manually.

4. **Run Notebooks: Open and run the Jupyter notebooks as needed for different projects.

Streamlit Deployment

Contributing

Feel free to fork this repository and submit pull requests with improvements or additional features. For any questions or issues, please open an issue on GitHub or contact me directly.