google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant

Add response_template to tokenizer_config.json (#4)

Update README (#5)

Update to canonical Gemma 4 chat template (#3)

Add Technical Report

Update config.json (#1)

Refactor: Update max_position_embeddings in text_config to 262144 (corrected formatting)

Preparing for release!