visible-cx
/

Gemma-4-12B-CoreAI

Text Generation

Model card Files Files and versions

Gemma-4-12B-CoreAI

55.3 GB

Ctrl+K

Ctrl+K

2 contributors

History: 21 commits

HiramKHackenbacker's picture

HiramKHackenbacker

v4: tied-table 12B — one bound vocab file, verify at the rungs that load, accepted_count, activations

50a5cd8 verified 3 days ago

dense2in-int8
Add dense2in-int8/gemma4_12b_qat_decode_int8lin_pf64 15 days ago
dense2in-pf64
Add dense2in-pf64/gemma4_12b_qat_decode_int4linsym_pf64 15 days ago
dense2in
dense2in: add the missing tokenizer/generation_config.json (fix by addition; byte-identical to the file the two dense2in-pf64 folders already ship) 14 days ago
tiered-v3
12B v3 manifest: register the verify role 4 days ago
tiered
tiered: ladder README (staged status, digests, per-rung requirements) 5 days ago
v4
v4: tied-table 12B — one bound vocab file, verify at the rungs that load, accepted_count, activations 3 days ago
.gitattributes

3.95 kB
v4: tied-table 12B — one bound vocab file, verify at the rungs that load, accepted_count, activations 3 days ago
README.md

26.1 kB
card: tiered-v3/ — an fp16 vocab path, seven rungs, prefill and verify 4 days ago