Nov 14 7 days ago 23:47 gen-cards: regenerate Use-it block for CoreAIKit 0.8.0; state that from CoreAIKit 0.8.0 a read with maxTokens above 1933 stops at 1933 tokens without an error Nov 13 8 days ago 19:14 README: keep maxTokens at 1933 or below (the decoder's 2048-position KV cache) Sep 25 00:28 gen-cards: regenerate Use-it block Sep 24 05:14 gen-cards: regenerate Use-it block Sep 14 18:37 Card: macOS/iOS 27 GA wording (beta requirement dropped; beta findings dated) Sep 7 10:42 Card: DeviceMark row (2026-09) Sep 5 04:17 Card: definition line (Core AI, 2026-09) Sep 4 15:23 Card: base_model_relation: quantized (so the conversion lists under the base model's Quantizations, not Finetunes) Aug 25 03:30 gen-cards: regenerate Use-it block Aug 15 05:15 Link the card back to its collection and the request box Aug 14 09:38 Add config.json so the Hub can count downloads Jul 24 00:47 gen-cards: regenerate Use-it block Jul 21 03:39 strip_debug_info rescue: 0.4.0 debug locations removed (fixes OS 27 beta 2+ load), weights/graph unchanged 03:38 strip_debug_info rescue: 0.4.0 debug locations removed (fixes OS 27 beta 2+ load), weights/graph unchanged Jul 3 06:09 gen-cards: regenerate Use-it block 06:01 Add gen-cards use-it markers (kit runner enrollment) Jun 23 01:59 Add R-SWA MoE decoder .aimodel (sym8) 01:42 Add embed_tokens table 01:41 Add DeepEncoder vision .aimodel (fp16) 01:38 Add tokenizer 01:38 Add arrangement assets 01:38 Add model card 01:38 initial commit