gemma4_e2b_qat_vl_vision.aimodel: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py
gemma4_e2b_qat_vl_decode_int4linsym_tbl: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py
gemma4_e2b_qat_vl_decode_int4linsym: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py
gemma4_e2b_qat_decode_int4lin_tbl: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py
gemma4_e2b_decode_int4lin_tbl: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py
- tokenizer/chat_template.jinja: copied from google/gemma-4-E2B-it-qat-q4_0-unquantized — the export script dropped it, so a host had no way to format prompts.
- eos_token: <eos> -> <turn|>. Gemma 4 ends a turn with <turn|>; <eos> ends the sequence, so a host stopping on it ran past the reply. Matches the Gemma-4-12B/31B bundles in this catalog.
Found by conversion/zoo_verify.py in github.com/john-rocky/coreai-model-zoo.
