Best of NLP — November 2024

  1. 1
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·1y

    A Crash Course on Building RAG Systems – Part 4

    Part 4 of the crash course on building RAG systems focuses on implementing RAG on multimodal data, specifically complex documents with tables, texts, and images. This series covers foundational components, evaluation methods, optimization techniques, and handling large data sets, making it highly beginner-friendly. Understanding how to build reliable RAG systems can reduce costs and enhance scalability for enterprises, bypassing the need for fine-tuning large language models (LLMs).

  2. 2
    Article
    Avatar of communityCommunity Picks·1y

    🤗 Transformers

    🤗 Transformers provides APIs and tools for easily downloading and training state-of-the-art pretrained models for tasks in natural language processing, computer vision, audio, and multimodal categories. It supports interoperability between PyTorch, TensorFlow, and JAX, allowing for flexible model training and deployment. The library also offers comprehensive documentation, tutorials, and guides to help users get started and achieve specific goals.

  3. 3
    Article
    Avatar of gcgitconnected·2y

    Let’s Build our own GPT Model from Scratch with PyTorch

    Learn how to build a basic Generative Pre-trained Transformer (GPT) model from scratch using PyTorch. This tutorial covers auto-regressive models, character-level tokenization, data batching, and training using text in the style of William Shakespeare. It provides a detailed implementation of a bi-gram language model including the use of multi-head attention, forward and training operations, and generating new text tokens.

  4. 4
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·2y

    A Crash Course on Building RAG Systems – Part 2

    Gain expertise in implementing RAG systems with this beginner-friendly guide. Part 2 builds on the foundations of Part 1, focusing on practical implementation. Learn how RAG systems address challenges in NLP and help bypass the costs of fine-tuning LLMs, offering enterprises significant cost savings. This crash course covers essential techniques and practical guidance for building reliable RAG applications.

  5. 5
    Article
    Avatar of mlmMachine Learning Mastery·2y

    A Practical Guide to Choosing the Right Algorithm for Your Problem: From Regression to Neural Networks

    This guide provides clear guidelines for selecting an appropriate machine learning algorithm based on the type of problem, data complexity, interpretability needs, and data volume. It features a question-based template for identifying the right algorithm and a table of real-world use cases with recommended algorithms and key considerations.

  6. 6
    Article
    Avatar of asayerasayer·2y

    10 Ways Prompt Engineering Transforms Development Work

    Prompt engineering involves designing specific and detailed prompts to interact effectively with Large Language Models (LLMs) like ChatGPT. By crafting precise instructions, software engineers can maximize the potential of AI, improving productivity and efficiency. Examples include providing detailed context, using synonyms, encouraging step-by-step solutions, role prompting, and more. Understanding the limitations of LLMs, such as computational constraints and potential inaccuracies, is also crucial.

  7. 7
    Article
    Avatar of hnHacker News·1y

    huggingface/smollm: Everything about the SmolLM & SmolLM2 family of models

    SmolLM2 is a family of compact language models ranging from 135M to 1.7B parameters, designed for on-device use with versatile capabilities. The SmolLM2-1.7B-Instruct model can be used as an assistant via various tools and frameworks. Detailed instructions for pre-training, fine-tuning, and using these models are provided. Additionally, the newly introduced SmolTalk dataset aids in building these models.

  8. 8
    Article
    Avatar of mlnewsMachine Learning News·2y

    A Comparison of Top Embedding Libraries for Generative AI

    Text embeddings, which convert textual data into dense vector representations, are crucial for various AI tasks including text, image, and audio processing. This post compares 15 popular embedding libraries such as OpenAI, HuggingFace, Gensim, Facebook, and AllenNLP, highlighting their strengths and limitations. The choice of library depends on specific use cases, computational needs, and the extent of required customization.

  9. 9
    Article
    Avatar of newstackThe New Stack·2y

    Top 7 Tools for Building Multimodal AI Applications

    Multimodal AI leverages large language models to simultaneously process various data types like text, images, and videos. Key models include OpenAI's CLIP, Meta AI’s ImageBind, DeepMind’s Flamingo, OpenAI’s GPT-4o, Runway’s Gen2, Google’s Gemini, and Anthropic’s Claude 3. These models are applied in tasks ranging from image annotation and caption generation to creating promotional videos and processing long-form data.

  10. 10
    Article
    Avatar of mlnewsMachine Learning News·2y

    Top 12 Python Libraries for Sentiment Analysis

    Sentiment analysis, which determines the emotional tone of text, is vital for understanding social media trends and consumer feedback. Python's rich library ecosystem provides tools like TextBlob, VADER, spaCy, NLTK, BERT, PyTorch, Flair, Scikit-learn, Transformers, Polyglot, Pattern, and Stanford CoreNLP to streamline sentiment analysis processes. These libraries offer various features, from simple APIs for beginners to complex models for advanced users, making sentiment analysis accessible and efficient across different applications.

  11. 11
    Article
    Avatar of dailydoseofdsDaily Dose of Data Science | Avi Chawla | Substack·2y

    A Crash Course on Building RAG Systems – Part 3

    Part 3 of the crash course on building RAG systems delves into optimizing RAG apps for real-world use cases. It focuses on reducing costs, driving revenue, scaling ML models, and predicting trends. The course is beginner-friendly and covers practical implementation strategies to build reliable RAG systems on LLMs.

  12. 12
    Article
    Avatar of do_communityDigitalOcean Community·2y

    MobiLlama: Your Compact Language Companion

    MobiLlama is a compact Small Language Model (SLM) with 0.5 billion parameters, designed for resource-constrained devices. It focuses on maintaining high performance while being energy-efficient, ensuring privacy, and reducing computational costs. Inspired by TinyLlama and Llama-2, MobiLlama integrates parameter sharing to optimize pre-training and deployment. It balances computational efficiency and the capability to understand complex language patterns, providing an efficient alternative to larger models like ChatGPT and Falcon.

  13. 13
    Article
    Avatar of itsfossIt's Foss·2y

    I Ran the Famed SmolLM on Raspberry Pi

    SmolLM is a series of efficient language models designed to run on local devices like the Raspberry Pi without compromising performance. Using a Raspberry Pi 5, the 1.7B parameter SmolLM model demonstrated impressive speed and accuracy, showcasing its potential for various applications, including mobile apps, customer support, educational tools, code assistance, and AI research. This shift towards local AI deployment enhances performance and privacy while reducing dependency on cloud-based services.

See all NLP archives