Fix config params to the true unique count (100,936). 106,568 is the file sum that double-counts the tied head; the README explains this.

Correct the card: the model is now trained on the 19.2 MB TinyStories validation set (the actual #17 request). Fixes param count (100,936 unique; the earlier 106,568 double-counted the tied head) and reports the honest memorization result (ratio 1.02x, verified reproducible).

Ship the correct Testr-100K model (trained on the 19.2 MB TinyStories validation set, as requested in #17). Replaces the wrong-data weights (191 MB web text). 100,936 unique params; memorized PPL 3.1540 vs never-seen 3.2203 (ratio 1.02x) — verified reproducible from this file.

Fix false 'fulfils request #17' claim: the model was trained on 191 MB web text, not the requested TinyStories-validation-only experiment. Published as a from-scratch demonstration, not the requested experiment.

Add model card (#4)

Add char vocabulary (128 chars + unk) (#3)

Add config (#2)

Add model weights (106,568 params, char-level GPT, 4 layers, 128-char vocab) (#1)

initial commit