all AI news
experimental-phi3-webgpu
May 9, 2024, 10:21 p.m. |
Simon Willison's Weblog simonwillison.net
Run Microsoft’s excellent Phi-3 model directly in your browser, using WebGPU so didn’t work in Firefox for me, just in Chrome.
It fetches around 2.1GB of data into the browser cache on first run, but then gave me decent quality responses to my prompts running at an impressive 21 tokens a second (M2, 64GB).
I think Phi-3 is the highest quality model of this size, so it’s a really good fit for running in a browser like this.
Via …
ai browser browsers cache chrome data experimental firefox generativeai homebrewllms llms microsoft phi phi-3 prompts quality responses running the browser think tokens webassembly webgpu work
More from simonwillison.net / Simon Willison's Weblog
Django Enhancement Proposal 14: Background Workers
1 day, 16 hours ago |
simonwillison.net
Why, after 6 years, I’m over GraphQL
2 days, 14 hours ago |
simonwillison.net
What does the public in six countries think of generative AI in news?
2 days, 17 hours ago |
simonwillison.net
Quoting Andrej Karpathy
2 days, 17 hours ago |
simonwillison.net
Jobs in AI, ML, Big Data
Senior Machine Learning Engineer
@ GPTZero | Toronto, Canada
ML/AI Engineer / NLP Expert - Custom LLM Development (x/f/m)
@ HelloBetter | Remote
Doctoral Researcher (m/f/div) in Automated Processing of Bioimages
@ Leibniz Institute for Natural Product Research and Infection Biology (Leibniz-HKI) | Jena
Seeking Developers and Engineers for AI T-Shirt Generator Project
@ Chevon Hicks | Remote
Cloud Data Platform Engineer
@ First Central | Home Office (Remote)
Associate Director, Data Science
@ MSD | USA - New Jersey - Rahway