VPVitou Phyindemystifyml.co·Dec 24, 2023 · 4 min readA Model that Retrieves Documents When in DoubtTL;DR: Active retrieval augmented generation system checks the quality of each sentence before outputting them. If the quality is questionable, it will retrieve additional documents and re-generate that sentence. Introduction The retrieval method su...00
VPVitou Phyindemystifyml.co·Dec 18, 2023 · 3 min readTraining MNIST with MLX on Apple Siliconimport mlx.core as mx import mlx.nn as nn import mlx.optimizers as optim import mnist device = mx.gpu mx.set_default_device(device) mx.default_device() # Device(gpu, 0) Dataset MNIST dataset contains 60,000 training samples of 28x28 images. Thes...00
VPVitou Phyindemystifyml.co·Jul 31, 2023 · 3 min readAugmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring TasksIntroduction In recent years, the advancement of natural language processing (NLP) models has revolutionized various language-related tasks, including sentence scoring and retrieval. Two prominent methods for scoring pairs of sentences are cross-enco...00
VPVitou Phyindemystifyml.co·Jul 25, 2023 · 2 min readLLaMA: Open and Efficient Foundation Language ModelsIntroduction The introduction of LLaMA, a large language model, aims to address the limited availability of open-sourced language models. Unlike many existing models, LLaMA is trained on open-source data, making it accessible for commercial use by an...00
VPVitou Phyindemystifyml.co·Jul 10, 2023 · 3 min readDeiT: Data-Efficient Image TransformerIntroduction The goal of this work is not to surpass the current state-of-the-art (SOTA) in image classification, but rather to advance the capabilities of image transformers. While Vision Transformer (ViT) introduced the idea of using transformers f...00
