Best of LLMJune 2023

  1. 1
    Article
    Avatar of aiplainenglishAI in Plain English·3y

    🦜️ LangChain + Streamlit🔥+ Llama 🦙: Bringing Conversational AI to Your Local Machine 🤯

    Large Language Models (LLMs) refer to machine learning models capable of producing text that closely resembles human language. These models have created exciting prospects, especially for developers working on chatbots, personal assistants, and content creation. LLaMA is a new large language model designed by Meta AI, which is Facebook’s parent company.

  2. 2
    Article
    Avatar of jetbrainsJetBrains·3y

    AI Assistant in JetBrains IDEs

    This week’s EAP builds of all IntelliJ-based IDEs and.NET tools include a major new feature: AI Assistant. The AI Assistant is powered by the JetBrains AI service. The service transparently connects you, as a product user, to different language models (LLMs) and enables specific AI-powered features.

  3. 3
    Article
    Avatar of mlnewsMachine Learning News·3y

    Microsoft AI Introduces Orca: A 13-Billion Parameter Model that Learns to Imitate the Reasoning Process of LFMs (Large Foundation Models)

    Microsoft AI Introduces Orca: A 13-Billion Parameter Model that Learns to Imitate the Reasoning Process of LFMs (Large Foundation Models) This innovative approach significantly improves the performance of existing state-of-the-art instruction-tuned models, addressing challenges related to task diversity, query complexity, and data scaling.

  4. 4
    Article
    Avatar of mlnewsMachine Learning News·3y

    Say Goodbye to Costly Auto-GPT and LangChain Runs: Meet ReWOO – The Game-Changing Modular Paradigm that Cuts Token Consumption by Detaching Reasoning from External Observations

    Large Language Models (LLMs) have catered their way into the challenging areas of Artificial Intelligence. ReWOO (Reasoning WithOut Observation) is a modular paradigm to reduce token consumption. The team has carried out a thorough analysis across six open Natural Language Processing (NLP) benchmarks and a curated dataset.