A new frontier for AI privacy in the cloud.

Important new study from Apple

Secure and private AI processing in the cloud poses a formidable new challenge. To support advanced features of Apple Intelligence with larger foundation models, we created Private Cloud Compute (PCC), a groundbreaking cloud intelligence system designed specifically for private AI processing. Built with custom Apple silicon and a hardened operating system, Private Cloud Compute extends the industry-leading security and privacy of Apple devices into the cloud, making sure that personal user data sent to PCC isn’t accessible to anyone other than the user — not even to Apple. We believe Private Cloud Compute is the most advanced security architecture ever deployed for cloud AI compute at scale.

Our new custom AI fuses advertising and behavioral science in one secure package.

Create user-facing experiences, new products, and new ways to work with the most advanced AI models on the market.

A full-featured, hackable Next.js AI chatbot built by Vercel

bryanheinz starred llmware-ai/llmware · llmware-ai/llmware Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models. Python 3.8k Updated May 14 via GitHub Public Timeline Feed https://ift.tt/2dvB1bN

bryanheinz starred rasbt/LLMs-from-scratch · rasbt/LLMs-from-scratch Implementing a ChatGPT-like LLM from scratch, step by step Jupyter Notebook 16.4k Updated May 15 via GitHub Public Timeline Feed https://ift.tt/2dvB1bN

bryanheinz starred armbues/SiLLM · armbues/SiLLM SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework. Python 145 Updated Apr 25 via GitHub Public Timeline Feed https://ift.tt/2dvB1bN

bryanheinz starred abi/secret-llama · abi/secret-llama Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3. TypeScript 2.1k 5 issues need help Updated May 11 via GitHub Public Timeline Feed https://ift.tt/2dvB1bN

bryanheinz starred ggerganov/llama.cpp · ggerganov/llama.cpp Port of Facebook's LLaMA model in C/C++ C 48.8k 12 issues need help Updated Jan 15 via GitHub Public Timeline Feed https://ift.tt/diuN1OR

Source: https://www.substratus.ai/blog/converting-hf-model-gguf-model/ I published this on our blog but though others here might benefit as well, so sharing the raw blog here on Github too. Hope it...

Find, download, and experiment with local LLMs

The BAIR Blog

We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary evaluation ...

bryanheinz starred mudler/LocalAI · mudler/LocalAI 🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade… C++ 15.1k Updated Jan 6 via GitHub Public Timeline Feed https://ift.tt/3eHsXz6

bryanheinz starred Hannibal046/Awesome-LLM · Hannibal046/Awesome-LLM Awesome-LLM: a curated list of Large Language Model 11k Updated Jan 5 via GitHub Public Timeline Feed https://ift.tt/3eHsXz6

bryanheinz starred apple/ml-ferret · apple/ml-ferret Python 6k Updated Dec 30, 2023 via GitHub Public Timeline Feed https://ift.tt/3eHsXz6

bryanheinz starred scaleapi/llm-engine · scaleapi/llm-engine Scale LLM Engine public repository Python 318 Updated Jul 22 via GitHub Public Timeline Feed https://ift.tt/cMr7Jaz

bryanheinz starred jmorganca/ollama · jmorganca/ollama Get up and running with large language models locally C 1.8k Updated Jul 22 via GitHub Public Timeline Feed https://ift.tt/cMr7Jaz

bryanheinz starred Significant-Gravitas/Auto-GPT · Significant-Gravitas/Auto-GPT An experimental open-source attempt to make GPT-4 fully autonomous. Python 135k 23 issues need help Updated May 24 via GitHub Public Timeline Feed https://ift.tt/0QGuaVT

bryanheinz starred lm-sys/FastChat · lm-sys/FastChat An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5. Python 18.4k 4 issues need help Updated May 6 via GitHub Public Timeline Feed https://ift.tt/MeGbcux

bryanheinz starred cocktailpeanut/dalai · cocktailpeanut/dalai The simplest way to run LLaMA on your local machine CSS 11.1k Updated May 6 via GitHub Public Timeline Feed https://ift.tt/MeGbcux

Leaked Internal Google Document Claims Open Source AI Will Outcompete Google and OpenAI