GenAIOps with Prompt Flow is a "GenAIOps template and guidance" to help you build LLM-infused apps using Prompt Flow. It offers a range of features including Centralized Code Hosting, Lifecycle Management, Variant and Hyperparameter Experimentation, A/B Deployment, reporting for all runs and experiments and so on.

official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives

Academic Information Retrieval and Automated Theory Development with Large Language Models

Bringing Language Models to the Most Resource Constrained Devices

[Interspeech2025] Official implementation of Neuro2Semantic A Transfer Learning Framework for Semantic Reconstruction of Continuous Language from Human Intracranial EEG

This Streamlit app, "LangChain ChatBot," invites users to input queries, utilizing the LangChain library and OpenAI's text-davinci-003 model to generate responses with controlled randomness. In just a click, users can explore the intriguing world of conversation through this compact and user-friendly interface.

Ever thought of talking to your Email Inbox, like talking to a Real-human 😲. Well, you can do it completely on Device!! 🔥🔥🔥 No privacy issues. I used Chroma with Docker, Mistral-7B-Instruct, and Ollama.

"Dive into Generative AI and Large Language Models (LLMs) with our comprehensive learning roadmap! Explore the world of AI generation, from fundamental concepts to advanced techniques, through a structured journey designed to enhance your understanding and expertise."

A tool for comprehensively evaluating and comparing responses from multiple large language models to provide actionable insights for improvement.

Evaluation of Google's Instruction Tuned Gemma-2B, an open-source Large Language Model (LLM). Aimed at understanding the breadth of the model's knowledge, its reasoning capabilities, and adherence to ethical guardrails, this project presents a systematic assessment across a diverse array of domains.

new method for discovering vulnerabilities that employs a variety of methodologies. This method combines self-attention with convolutional networks to record both local, position-specific features and global, content-driven interactions

This repo is used for Speech to Text with offline saved customizable dictionary.

LLMs Zoomcamp by DataTalks Club

This repo contains influential papers which use finetuning techniques for LLMs for domain specific tasks.

This study aims to fill this gap created by the exponential growth of digital content by evaluating the performance of selected LLMs in terms of summarization quality, using automated evaluation metrics. The goal is to identify the most effective models for generating accurate and human-like summaries, providing valuable insights for practitioners.

Large Language Model for Automatic Repair of Security Vulnerabilities in Python Source Code

This project utilizes a machine learning model where consumer brand data is employed. Initially, a preliminary model is developed, followed by a refined model using a process called 'fine-tuning' to improve results. Additionally, a comprehensive testing suite has been created to validate accuracy and reliability of the model's predictions.

LLM-based variant extraction from title and abstracts of biomedical publications. Search literature-derived co-associations between variants, cancers, and treatments