Fetching metadata from the HF Docker repository...
Jun 15 22:40 Pre-deadline audit: honest sealed-test numbers in parse hint + model card, lookup timeout, roofline cache fix 22:29 Update README.md 22:17 README: add demo video + social post links (Post it requirement) 21:39 Apple: grey out the VRAM box on Mac (unified memory only) 21:37 Apple: unified-memory label + chip options without misleading GB 21:30 Fix: re-parsing a machine without a GPU now clears the previous GPU selection 21:19 spec parser: GPU duration back to 120s (within ZeroGPU cap) 21:16 Fix spec-parser cold-start hang: pre-cache weights at boot 20:58 Add achievement:fieldnotes tag (blog published) 18:09 Buy advice: mini-PC category now starts at a $249 Jetson, real cheap-to-big ladder 17:54 Buy advice: verified, dated prices with live price links per build 17:44 Fix buy advice: Minimum and Comfortable are now distinct builds 17:38 Polish buy-card 'What to look for' into an iconed spec sheet 17:30 Restore line icons + brand-coloured logos (NVIDIA/Windows/Apple etc.) 17:18 Reskin: CRT-pixel technical-instrument UI (dense option table, roofline centerpiece, pixel icons, phosphor-green, no emoji/em-dash) 16:13 Audit remediation: XSS fix, pinned loaders, engine bug fixes, honest claims, head_dim KV, hackathon tags Jun 14 16:55 Vision/diffusion compute-roofline speed (FPS + s/image); fine-tune VRAM validation+sweep; flag-gated eager model load 14:44 Laptop/Mobile NVIDIA GPUs with correct VRAM and bandwidth 14:03 Honest non-LLM lookups, realistic speeds, clearer gauge, custom/URL coupling, runner icon 13:16 Full model-URL breakdowns, gauge clarity, CPU honesty, multi-platform buying guide, chart tooltips, runner icon 12:37 Catalogue now 110 official models; GGUF size fix 12:25 Interactive results, working priority, fine-tuning mode, honest custom + model lookup Jun 10 20:58 Per-position accent borders on the use-case pills 20:51 GPU spam guard (serialize + button lock), live progress tickers, describe-first layout, real-machine bindings, chart fix for custom VRAM 20:30 Fix spec-parser GPU window; clearer chart colours, unclipped label 19:19 Paste box goes live: fine-tuned spec parser fills the form from messy text 13:29 Load speed predictor via xgboost native format 13:27 Speed predictions now come from a model trained on 6.6k real measurements (17.5% median error on unseen hardware), physics formula beyond its measured range 12:28 Speed predictions with receipts: bandwidth roofline, real-runs chart, honest provenance Jun 9 22:58 Multi-goal checks (union buying advice), fix vision/audio quality bars, honest niche fallback 22:29 Add einops for the Mamba hub kernel 22:26 Fix kernels version clash: pin to transformers' declared range 22:23 Real catalogue: 83 verified models, buy-advice mode, live model lookup, license-aware cards 22:07 Speed up explainer: prebuilt Mamba kernels (transformers 5.8 + kernels hub), tighter answer budget 20:49 Deploy FitCheck: engine + Nemotron model brick on ZeroGPU 20:36 Deploy FitCheck: engine + Nemotron model brick on ZeroGPU 13:35 Deploy FitCheck UI brick 13:34 initial commit