Data Science Assignment, Decision Tree Credit Card Fraud Detection

This toolkit provides scripts, examples, and utilities to facilitate the process of adapting OpenAI/Gemini to handle summarization/classification task.

Text Classfication using BERT

A simple example of fine tuning Gemma 2 2B instruct using DoRA / LoRA

fine-tune LLaMA and BERT using the PEFT (Parameter-Efficient Fine-Tuning) method and LoRA (Low-Rank Adaptation) in Python.

A LLM-based chatbot can solve math problems, give clearly explainable reasons and self-training by using reinforcement learning, Fine-tune Mistral v0.3 (7B) on MathQA-40K datasets, Use Unsloth framework for increasing performance model, speed training time, Apply Google Mind paper’s techniques for increasing accuracy and performance of model

Implement of Behavior Cloning (BC) and Conservative Q-Learning (CQL) algorithms for training reinforcement learning models using a dataset of state-action pairs. It provides an environment for experimenting with these algorithms, comparing their performance, and analyzing the effects of different parameters and dataset variations on training result

Provides a Dockerfile and instructions in order to facilitate the process of training/fine-tuning a custom text-to-speech (TTS) model using Piper TTS

This repository contains a PyTorch implementation of a Convolutional Neural Network (CNN) for classifying the MNIST dataset. The project explores different fine-tuning techniques, including LoRA (Low-Rank Adaptation), DoRA (Dynamic Low-Rank Adaptation), and QLoRA (Quantized Low-Rank Adaptation), to improve model performance and efficiency.

ML LEARNING

This repository features a fine-tuned Whisper model for accurate and efficient audio transcription. Designed to handle various languages, the model processes audio files and provides real-time transcriptions.

Fine tuning LLaMA with LoRA

Speak the best with your models!

This is a public dataset for training OCR models on using the British Parliament's historic records. It is for digital humanities researchers

A Novel Approach for Alzheimer's Classification Utilizing Ensemble Learning on Pre-trained Neural Networks Fine-tuned on Pre-processed and Augmented Alzheimer's Dataset

TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.

An Autonomous SRE System powered by a Tri-Brain Architecture: Reflex (Transformer), Reasoning (SLM), and Adaptive (Reinforcement Learning).

The Moment | 片刻即永恒

A wrapper library for LeapAI's APIs to make integrating AI into your .NET apps a breeze

A Novel Optimized ResNet-SD Model for Brain Tumor Classification Using Stochastic Depth and Metaheuristic Optimization