Viewing profile — gbickford

Small models don't "know" as much so they hallucinate more. They are better suited for generations that are based in a ground truth, like in a RAG setup. A better comparison might …

It's for visualizing datasets where fine-grained cluster details and broader relationships matter. There are example renderings in the paper. From the README: > PaCMAP (Pairwise Co…

> Create Hello World application: > sudo mgrg -i -u $(whoami) helloworld Why does it need sudo to compile?

If you look in the `config.json`[1] it shows `Zamba2ForCausalLM`. You can use a version of the transformers library to do inference that supports that. The model card states that y…

This article is from 2017

This is true. Devs are looking for frameworks. See CrewAI who refuses to allow users to disable some pretty aggressive telemetry, yet they have a huge number of GH stars. The abstr…

It's always disappointing when people publish things to GitHub without the intention of collaborating or sharing.

I couldn't find any training code in the MXL examples.

> Relationship with CVNets > CoreNet evolved from CVNets, to encompass a broader range of applications beyond computer vision. Its expansion facilitated the training of foundationa…

It's a thing in Chrome Dev Tools now: https://developer.chrome.com/docs/devtools/coverage/

There's gotta be somewhere in the middle. Vercel's movements feel a lot like the "Embrace, extend, and extinguish" playbook. Maybe there is a class of developer out there that does…

Llama.cpp is an inference engine. The author of llama.cpp designed gguf. Funcionary is a model that does function calling. You can download functionary weights in the gguf format a…

Have you tried generating two sets of qapairs, one with bad answers, and using DPO?

The authors don't seem to care about the principle of least privilege: https://github.com/ollama/ollama/issues/851#issuecomment-177... It makes me wonder what other security issues…

This paper is well written. The results are pretty wild. They observed some amazing reduction in training resources required to achieve similar benchmarks to models trained on conv…