honest NVIDIA path (Nemotron-Mini-4B 5/5) + bake-off table + Modal runtime serving + 3-tier fallback + SFT dataset

tags+evidence: achievement:welltuned + sponsor:modal (Modal-trained LoRA published to HF, verified) + NVIDIA NIM recipe

tags+evidence: sponsor:openbmb + sponsor:nvidia (MiniCPM + Nemotron via Nebius, live-verified)

tags: add track:wood (multi-track) + achievement:llama (offgrid runs via llama.cpp)

Update README.md

link published Field Notes blog post

cite reproducible offgrid transcript

cite offgrid proof in README

submission: demo+social links, tiny-titan/llama/offgrid/openai tags, four backends

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Deploy Unstuck (Codex-built) — initial code

initial commit