Curious on what backs this assertion. As a counterpoint we’ve been running 200+ models in production for more than 5 years - language models, embedding, classifiers, low tens to hundred M params. Traffic in the order of 1-2M requests/day and everything is enabled by onnx with some cgo (or Rust) plumbing on top. What’s your SLA?
Thanks a lot for this. Also one question in case anyone could shed a bit of light: my understanding is that setting temperature=0, top_p=1 would cause deterministic output (identical output given identical input). For sure it won’t prevent factually wrong replies/hallucination, only maintains generation consistency (eq. classification tasks). Is this universally correct or is it dependent on model used? (or downright wrong understanding of course?)
- a collection of effects (various distortions, color glitches, demoscene-like) applied over incoming video stream, maximum of 4 effects stackable on top of one another
- midi controllers support (controlling actions/params of effects via CC)
- modulation of effects params via LFO and audio events (bpm, kick, tonal detection)
- loading of .glsl shaders (eq. shadertoy.com)
- dynamic input resolution, output either 360p (rpi 4/5) or upscaled to 720p / 1080p (networks like SRGAN over Hailo / RPI or RK3588 with a Radxa 5B SBC).
Given a 2nd screen (timeline editor) would love to evolve this to something like a hardware editor, somewhat in the line of DAWs in the audio world. Most things are working with biggest challenge now being building a control surface (buttons, rotaries + associated oleds, etc) and attempting laying it all on a PCB, a process I don't know much about. If there's interest welcome comments and could elaborate more.
first $100: pdf photography courses with weekly chapters
first $1000+: built a shop selling silk scarves (100-odd) I collected myself from Laos/Cambodia/Thailand to balance trip budget (25yo back then, mad travelling). Sold all scarves, closed shop.
This. Same scenario here, fondly remember 1080ti, that was the workhorse for us alongside cloud training (startup with ~100 nlp prod models, ner, siamese, count models, etc). ULMFiT and language transfer was the moment when upgrades felt necessary though 2080ti’s vram unfortunately stayed the same (never had access to Titans for instance so perspective may be limited).
Signed it too :) Can’t remember a particular reason though in our case (former cofounder) we were discovering the actor model, immutability, streams,.. tbh remember a great deal of fun programming during those days, insane schedules and whatnot. Though truth be told our most productive systems are Go these days (sold, stack still holding).
Agree, this being a cyber-fraud company I believe one could keep a team busy for a long time focusing on building secure systems rather than operating them to the point where no-one gets to see what's actually being stored within. The paper trail though I'm still puzzled about, he couldn't have acted alone.
Man, don't beat yourself up. Americans are great people and not that bad of a society now. (someone in a WE society). Hang in there, we'll bicker after :)
You could have a look at ArangoDB (https://www.arangodb.com), a multi-model database - it may cover your use cases. Hopefully linking is ok in comments, will remove if its breaks community rules - no affiliation etc..