card: recipe and collection links

Card: One name (While, whileai SDK), current links (#1)

Rebrand to While AI

Update README.md

Update README.md

Developed by Zero Proof Labs; brand spacing; remove payments tag

Update chart

Update results

Refresh adapter config

Refresh weights

Ship the system prompt template (identical to the 1B's)

Add canonical results chart

Model card: canonical macro-averaged results (run with matched 11,131/1,977 train-eval split), corrected method description and chart

add 0.5B QLoRA adapter weights + tokenizer

simplify Get Started snippet (AutoPeftModel one-liner, no explicit base load)

reformat to official HF model-card template

scrub none mentions, add chart

add branded 0.5B chart (frontier reused)

0.5B model card: Qwen2.5-0.5B QLoRA, class-balanced

initial commit