llm

A list of posts tagged llm

Blogs

• Configure Ollama on Dev Containers and VS Code
• Getting started with Ollama on Windows
• Using Generative AI to produce Spotify Clips

Notes

Responses

• Self-Adapting Language Models (SEAL)
• The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation
• Introducing Command A
• Simon Willison's AI-Generated Tools Colophon
• Introducing Mercury, the first commercial-scale diffusion large language model
• The Ultra-Scale Playbook: Training LLMs on GPU Clusters
• LangChain State of AI 2024 Report
• Microsoft Research: Introducing DRIFT Search
• Thinking LLMs: General Instruction Following with Thought Generation
• Bringing Llama 3 to life
• Home-Cooked Software and Barefoot Developers
• Meta Large Language Model Compiler: Foundation Models of Compiler Optimization
• Mapping the Mind of a Large Language Model
• Ultravox - An open, fast, and extensible multimodal LLM
• Reproducing GPT-2 (124M) in llm.c in 90 minutes for $20
• Introducing Snowflake Arctic
• Introducing Phi-3
• Introducing Llama 3
• RecurrentGemma - Open weights language model from Google DeepMind, based on Griffin.
• Hello OLMo: A truly open LLM
• LLM training in simple, raw C/CUDA
• ARAGOG: Advanced RAG Output Grading
• OpenAI - Introducing improvements to the fine-tuning API and expanding our custom models program
• Introducing Command R+: A Scalable LLM Built for Business
• IPEX-LLM
• Start using ChatGPT instantly
• Announcing DBRX: A new standard for efficient open source LLMs
• Mamba: Linear-Time Sequence Modeling with Selective State Spaces
• Demystifying Embedding Spaces using Large Language Models
• Ollama now supports AMD graphics cards
• You can now train a 70b language model at home
• Levels of Complexity: RAG Applications
• Inflection-2.5: meet the world's best personal AI
• Training great LLMs entirely from ground up in the wilderness as a startup
• Gemma PyTorch
• Introducing the next generation of Claude
• GGUF, the long way around
• Predictive Human Preference: From Model Ranking to Model Routing
• The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
• Announcing Mistral Large
• GPT in 500 lines of SQL
• Gemma: Introducing new state-of-the-art open models
• Cosmopedia v0.1
• Ollama - Windows Preview
• NVIDIA Chat with RTX
• Memory and new controls for ChatGPT
• Google’s Hugging Face deal puts ‘supercomputer’ power behind open-source AI
• New OpenAI embedding models and API updates
• NightShade
• Introducing Stable LM 2 1.6B
• Talking about Open Source LLMs on Oxide and Friends
• LeftoverLocals: Listening to LLM responses through leaked GPU local memory
• More than an OpenAI Wrapper: Perplexity Pivots to Open Source
• Generative AI and .NET - Part 2 SDK
• Generative AI and .NET - Part 1 Intro
• Supporting the Open Source AI Community
• GPT-4 API general availability