QLoRA (quantized LoRA)
QLoRA (quantized LoRA) is a machine learning technique that combines quantization and Low-Rank Adaptation to efficiently fine-tune large language models with reduced computational resources while maintaining performance.
Artificial Intelligence
Hugging Face
Hugging Face is an open-source company specializing in natural language processing and artificial intelligence tools. It is known for its development and maintenance of the Transformers library, which provides state-of-the-art machine learning models for a variety of applications.
Kinetics (human action dataset)
Kinetics is a large-scale dataset designed for action recognition, consisting of thousands of video clips categorized into various human actions.
ImageNet
ImageNet is a large visual database designed for use in visual object recognition software research, playing a significant role in advancing machine learning.
Herbert A. Simon
Herbert A. Simon was an American polymath known for his contributions to economics, psychology, artificial intelligence, and cognitive science. He was awarded the Nobel Prize in Economics in 1978 for his research into decision-making processes within economic organizations.
Comma.ai (open-source driving dataset)
Comma.ai is an open-source driving dataset designed to assist in the development of autonomous vehicle technologies, providing a valuable resource for researchers and developers.
Feature visualization
Feature visualization is a technique in machine learning that helps interpret complex models by visualizing the features learned by the model.
ColBERT (contextualized late interaction over BERT)
ColBERT (Contextualized Late Interaction over BERT) is a neural information retrieval model that leverages BERT embeddings combined with a novel late interaction mechanism to efficiently rank documents based on query relevance. It aims to balance retrieval effectiveness with computational efficiency.
Top-k sampling
Top-k sampling is a probabilistic method used in natural language processing to generate text by selecting the next word from the k most likely options. It balances creativity and coherence in language models by limiting the choice to a subset of probable candidates.
EMNIST
EMNIST (Extended MNIST) is a dataset for handwritten character recognition, extending the original MNIST dataset with additional characters and complexity.