Simon Willison’s Weblog

Announcing Open Flamingo (via) New from LAION: “OpenFlamingo is a framework that enables training and evaluation of large multimodal models (LMMs)”. Multimodal here means it can answer questions about images—their interactive demo includes tools for image captioning, animal recognition, counting objects and visual question answering. Theye’ve released the OpenFlamingo-9B model built on top of LLaMA 7B and CLIP ViT/L-14—the model checkpoint is a 5.24 GB download from Hugging Face, and is available under a non-commercial research license.

# 9:59 pm / ai, generative-ai, llama, laion, llms, clip

Cerebras-GPT: A Family of Open, Compute-efficient, Large Language Models (via) The latest example of an open source large language model you can run your own hardware. This one is particularly interesting because the entire thing is under the Apache 2 license. Cerebras are an AI hardware company offering a product with 850,000 cores—this release was trained on their hardware, presumably to demonstrate its capabilities. The model comes in seven sizes from 111 million to 13 billion parameters, and the smaller sizes can be tried directly on Hugging Face.

# 10:05 pm / open-source, ai, gpt-3, generative-ai, local-llms, llms, cerebras, llm-release, gpt

Quicker serverless Postgres connections. Neon provide “serverless PostgreSQL”—autoscaling, managed PostgreSQL optimized for use with serverless hosting environments. A neat capability they provide is the ability to connect to a PostgreSQL server via WebSockets, which means their database can be used from environments such as Cloudflare workers which don’t have the ability to use a standard TCP database connection. This article describes some clever tricks they used to make establishing new connections via WebSockets more efficient, using the least possible number of network round-trips.

# 10:09 pm / postgresql, websockets

gpt4all. Similar to Alpaca, here’s a project which takes the LLaMA base model and fine-tunes it on instruction examples generated by GPT-3—in this case, it’s 800,000 examples generated using the ChatGPT GPT 3.5 turbo model (Alpaca used 52,000 generated by regular GPT-3). This is currently the easiest way to get a LLaMA derived chatbot running on your own computer: the repo includes compiled binaries for running on M1/M2, Intel Mac, Windows and Linux and provides a link to download the 3.9GB 4-bit quantized model.

# 6:03 pm / open-source, ai, generative-ai, llama, local-llms, llms, fine-tuning

Making SQLite extensions npm install’able for Node.js, and on deno.land/x for Deno (via) Alex Garcia figured out how to get his “pip install X” trick for distributing compiled SQLite extensions to work for Node too! Now you can “npm install” 10 of his extensions, including sqlite-regex and sqlite-xsv and sqlite-http and sqlite-html and more, and attach them to a node-sqlite3 or better-sqlite3 connection. He’s bundled them for Deno too!

# 10:13 pm / nodejs, sqlite, npm, deno, alex-garcia

Schillace Laws of Semantic AI (via) Principles for prompt engineering against large language models, developed by Microsoft’s Sam Schillace.

# 12:20 am / ai, prompt-engineering, generative-ai, llms

Downloading and converting the original models (Cerebras-GPT) (via) Georgi Gerganov added support for the Apache 2 licensed Cerebras-GPT language model to his ggml C++ inference library, as used by llama.cpp.

# 4:28 am / llama, local-llms, llms, cerebras, llama-cpp, georgi-gerganov

How to use AI to do practical stuff: A new guide (via) Ethan Mollick’s guide to practical usage of large language model chatbot like ChatGPT 3.5 and 4, Bing, Claude and Bard is the best I’ve seen so far. He includes useful warnings about common traps and things that these models are both useful for and useless at.

# 6:17 am / bing, ai, chatgpt, bard, llms, ethan-mollick, claude