LangChain - Integrating External Documents and SQL with GPT-4
Dive into LangChain's capabilities for integrating external documents and SQL with GPT-4, learning to chain multiple data sources and leverage advanced language models effectively.
The ALPACA Code: Self-Instruct Fine-Tuning of Large Language Models
Dive into the technical implementation of self-instruct fine-tuning for Large Language Models using ALPACA, covering synthetic dataset generation and parallel task optimization.
Creating Self-Instruct Data Sets for LLM Fine-Tuning with ChatGPT
Master the creation of synthetic instruction datasets using ChatGPT and GPT-4 for fine-tuning language models, covering data generation, multi-task training, and task decomposition techniques.
Self-Instruct Fine-Tuning of Large Language Models - Introduction to Alpaca
Master self-instruct fine-tuning techniques for LLMs, focusing on synthetic data generation using ChatGPT/GPT-4 to enhance model performance in specific tasks like summarization and translation.
Using MPT-7B in Hugging Face and LangChain
Explore MPT-7B LLM implementation in Hugging Face and LangChain, covering setup, initialization, tokenization, and text generation. Learn to leverage open-source models for AI applications.
Build Conversational Agents with Vector DBs - LangChain
Learn to create powerful conversational agents using vector databases and LangChain, combining retrieval augmentation with chatbots for enhanced data freshness and domain-specific knowledge.
Testing Starcoder for Reasoning with PAL
Explore StarCoder's reasoning capabilities and compatibility with PAL Chain in LangChain through demonstrations, code examples, and practical tests.
StarCoder - The LLM to Make You a Coding Star
Explore StarCoder's advanced code generation capabilities, including continuous coding and gap-filling. Learn about its applications, versions, and impressive 8,000-token sequence length for enhanced coding assistance.
LangChain + Retrieval Local LLMs for Retrieval QA - No OpenAI
Explore LangChain for retrieval QA using local language models like Flan T5-XL, FastChat-T5, StableVicuna, and WizardLM, without relying on OpenAI services.
Llama Index - Step by Step Introduction
Step-by-step guide to using Llama Index for document storage, indexing, and querying with customizable LLM settings and prompt helpers. Learn to create, manage, and interact with vector store indexes efficiently.
QA Over Documents with Auto Vector Index Selection with Langchain Router Chains
Learn to automatically select vector indexes and prompts for document QA using Langchain router chains, with code demos for Streamlit and terminal applications.
Inside ChatGPT- Unveiling the Training Process of OpenAI's Language Model
Explore the training process behind ChatGPT, including generative pretraining, supervised fine-tuning, and reinforcement learning through human feedback. Gain insights into AI language model development.
How Replit Trained Their Own LLMs - LLM Bootcamp
Comprehensive guide to training custom LLMs: from data processing and tokenization to evaluation and deployment, with insights on tools, best practices, and essential skills for LLM engineers.
Agents Masterclass from LangChain Founder - LLM Bootcamp
Explore tool-using language models with long-term memory in this comprehensive overview of AI agents, covering key concepts, challenges, and real-world examples from LangChain's co-creator.
Richard Socher on NLP at Salesforce - Full Stack Deep Learning - March 2019
Explore cutting-edge NLP applications at Salesforce with Richard Socher, discussing deep learning advancements and their impact on natural language processing in enterprise settings.
Accelerating High-Performance Machine Learning at Scale in Kubernetes
Hands-on guide for deploying optimized machine learning models in cloud native ecosystems, focusing on GPT-2 NLP model deployment in Kubernetes using ONNX Runtime and Seldon Core Triton server.
AI as CEO: From Skepticism to Optimism - Lessons from a Startup Experiment
Explore an entrepreneur's journey of empowering AI as a startup CEO, challenging perceptions and navigating the balance between AI optimism and caution in shaping our future.
FATE-LLM - Empowering Large Language Models with Federated Learning
Explore FATE-LLM, integrating federated learning with large language models to address data privacy concerns. Learn about its components, implementation on Kubernetes, and real-world applications.
The Future of AI: Dream or Nightmare? - 2023 Christmas Lectures - Lecture 3
Explore AI's future with experts, examining opportunities and challenges as it evolves. Gain insights into potential impacts and developments in this rapidly advancing field.
The Truth About AI: My AI Life - 2023 Christmas Lectures - Lecture 2
Professor Mike Wooldridge explores AI's pervasive role in daily life, revealing its current applications and impact. The lecture offers insights into AI's present capabilities and future potential.
Phi-2: Small Language Model Performance Tutorial - Google Colab with Python
Explore Microsoft's Phi-2, a compact yet powerful language model outperforming larger counterparts. Learn its training methods and test capabilities in coding, math, reasoning, and data extraction using Google Colab.