Best of NLP — March 2024
- 1
- 2
- 3
- 4
Community Picks·2y
Python String Methods
This post introduces Python string methods, including basic methods for case adjustment, searching and replacing, trimming, splitting and joining, advanced manipulations, and subtly different methods for decimals, digits, and numerics. It also mentions new additions in Python 3.9 for removing prefixes and suffixes from strings.
- 5
GoPenAI·2y
A Step-by-Step Guide to Creating a Large Language Model from scratch…
This post provides a step-by-step guide to creating a Large Language Model (LLM) from scratch using the Transformer architecture and TensorFlow/Keras. It also explains how to implement transfer learning with Hugging Face.
- 6
freeCodeCamp·2y
How to Build Better AI Workflows with Langchain
Learn how to use Large Language Models like ChatGPT in your app with Langchain. Langchain is a powerful tool that simplifies building and deploying large language models, allowing you to integrate multiple services and enhance functionality. With Langchain, you can access and learn from newer data without limits.
- 7
- 8
Medium·2y
TinyLlama Is An Open-Source Small Language Model
TinyLlama is an open-source small language model designed to enable end-user applications on mobile devices and test innovative ideas related to language models. It demonstrates remarkable performance and aims to provide a lightweight solution for various applications and scenarios.
- 9
An Introduction to Mistral AI
Mistral AI is an advanced AI technology specializing in processing and generating human-like text. Its use cases include content creation, customer support, education, and translation. Mistral AI offers newer algorithms, customization, and better context windows compared to ChatGPT.
- 10
Hacker News·2y
lavague-ai/LaVague: Automate automation with Large Action Model framework
LaVague is a framework designed to automate menial tasks on behalf of users by transforming natural language instructions into seamless browser interactions. It is built on open-source projects, integrates with Selenium, and supports local models for privacy and control.
- 11
The Basics of AI-Powered (Vector) Search
This post explores the basics of AI-powered search engines, including the components of search engines, lexical retrieval, and the limitations of BERT embeddings for semantic search. It introduces sBERT as a solution to improve the semantic meaningfulness of BERT embeddings and provides information on siamese and triplet networks. The post also discusses the Sentence Transformers library and how it can be used for vector search and ranking. It concludes with information on making sBERT multilingual and the BEIR benchmark for information retrieval.
- 12
BERT Explained – The Key to Advanced Language Models
BERT is an advanced method developed by Google for natural language processing. It allows computers to understand the contextual meaning of words in a sentence and has applications in improving search engines, translation services, and generating human-like text.
- 13
KDnuggets·2y
Getting Started With Claude 3 Opus That Just Destroyed GPT-4 and Gemini
Anthropic has released a new series of large language models called Claude 3 that have outperformed GPT-4 and Gemini in benchmark tests. The models come in three variants: Haiku, Sonnet, and Opus. Claude 3 models have enhanced vision capabilities and can process various visual formats. To start using the latest Claude 3 model, you can create a new account on the Anthropic website.
