LangChain has many advanced retrieval methods to help address these challenges. (1) Multi representation indexing: Create a document representation (like a summary) that is well-suited for retrieval (read about this using the Multi Vector Retriever in a blog post from last week). (2) Query transformation: in this post, we'll review a few approaches to transform humans questions in order to improve retrieval. (3) Query construction: convert human question into a particular query syntax or language, which will be covered in a future post
This article provides an introduction to Mlflow, an open-source platform for end-to-end machine learning lifecycle management. The article focuses on using MLflow as an orchestrator for machine learning pipelines, explaining the importance of managing complex pipelines in machine learning projects.
This article discusses TinyLlama, an open-source project for a smaller language model with around 1.1B parameters, capable of complex tasks with less memory usage. The article covers implementation, testing, and performance analysis.
This GitHub repository contains a course on Large Language Models (LLMs) with roadmaps and Colab notebooks. The course is divided into three parts: LLM Fundamentals, The LLM Scientist, and The LLM Engineer. Each part covers various topics, including mathematics, Python, neural networks, instruction datasets, pre-training, supervised fine-tuning, reinforcement learning from human feedback, evaluation, quantization, new trends, running LLMs, building a vector storage, retrieval augmented generation, advanced RAG, inference optimization, and deployment.
This article explores how to boost the performance of small language models by using supervision from larger ones through knowledge distillation. The article provides a step-by-step guide on how to distill knowledge from a teacher model (LLama 2–70B) to a student model (Tiny-LLama) using unlabeled in-domain data and targeted prompting.
ColBERT is a new way of scoring passage relevance using a BERT language model that substantially solves the problems with dense passage retrieval.
- Embeddings transform words and sentences into sequences of numbers for computers to understand language.
- This technology powers tools like Siri, Alexa, Google Translate, and generative AI systems like ChatGPT, Bard, and DALL-E.
- In the early days, embeddings were crafted by hand, which was time-consuming and couldn't adapt to language nuances easily.
- The 3D hand-crafted embedding app provides an interactive experience to understand this concept.
- The star visualization method offers an intuitive way to understand word embeddings.
- Machine learning models like Word2Vec and GloVe revolutionized the generation of word embeddings from large text datasets.
- Universal Sentence Encoder (USE) extends the concept of word embeddings to entire sentences.
- TensorFlow Projector is an advanced tool to interactively explore high-dimensional data like word and sentence embeddings.
- This technology powers tools like Siri, Alexa, Google Translate, and generative AI systems like ChatGPT, Bard, and DALL-E.
- In the early days, embeddings were crafted by hand, which was time-consuming and couldn't adapt to language nuances easily.
- The 3D hand-crafted embedding app provides an interactive experience to understand this concept.
- The star visualization method offers an intuitive way to understand word embeddings.
- Machine learning models like Word2Vec and GloVe revolutionized the generation of word embeddings from large text datasets.
- Universal Sentence Encoder (USE) extends the concept of word embeddings to entire sentences.
- TensorFlow Projector is an advanced tool to interactively explore high-dimensional data like word and sentence embeddings.
With all the hype around AI/ML in observability, it's more likely than ever that companies benefit from storing and viewing data in one system and training ML models in another.
