Stories by lewq

Show HN: Local "GPTs" with Knowledge and API calling, one-liner install

Show HN: Helix apply -f deploy YAML GenAI with RAG and APIs on local open models [video]

AISpec: Declarative config for LLM app patterns?

Can we help you build an AI App?

RAG, fine-tuning, API calling and gptscript for Llama 3 running locally

Show HN: Smart website search powered by open models

Deploy gptscript to prod with 'git push'

Bootstrapped SaaS startup: New limits on fine tuning on Helix free plan

How we got fine-tuning Mistral-7B to not suck

Type error in AI? Can models be intelligent or are they the same thing as maps?

UI for fine tuning Mistral and SDXL, GPU mem/latency optimization

Show HN: Local fine tuning for Mistral and SDXL, GPU mem/latency optimization

Understanding classifier-free guidance for style transfer

Show HN: MLflow to KFServing image builds with Kaniko on K8s

ML data and model drift in Prometheus and Grafana

Dotscience is shutting down

Run tracking liberates ML teams

Dotmesh hiring good communicators and systems programmers globally

Commit directly to master. Dotmesh engineering principles

Capture the state of many μ-services' DBs in a single commit

1 2