TitanPythons/Qwen3.5-VL-2B-8bit-MLX-CRACK

Add Ko-fi support section

Add vMLX promotional banner to README

Add vMLX promotional banner to README

Update: increase repetition_penalty to 1.3, add presence_penalty 1.5 per Qwen recommendation

Fix: inject chat_template with enable_thinking support into tokenizer_config.json

Fix standalone/spec-decoding positioning in README

Remove proprietary methodology details

Add dealign_logo.png

Add dealign_mascot.png

Add README with model card

CRACK 2B: FA+SSM surgery, thinking-off default, EOS fixed

initial commit