mlboydaisuke
/

gemma-4-E2B-CoreAI

Text Generation

custom-metal-kernels

Model card Files Files and versions

gemma-4-E2B-CoreAI

34.3 GB

Ctrl+K

Ctrl+K

1 contributor

History: 50 commits

mlboydaisuke's picture

Add the chat template and stop at the end of a turn

3fdd06d verified 7 days ago

gpu-pipelined-b2
Add the chat template and stop at the end of a turn 7 days ago
gpu-pipelined
Add the chat template and stop at the end of a turn 7 days ago
ios-ane
ios-ane: revert to the device-verified bucket-64 chunk set (the bucket-512 set jetsams the on-device ANE first compile) about 2 months ago
ios-frontend
E2B QAT gather tables (checkpoint-derived - pair with the QAT bundles) about 2 months ago
ios-gpu
iOS GPU best: int4-kmeans head+argmax kernel about 2 months ago
macos
macOS best: head+argmax kernel (int8) about 2 months ago
.gitattributes

6.95 kB
Add b2 (beta3-loadable) bundle under gpu-pipelined-b2/gemma4_e2b_qat_decode_int4lin_tbl_aotc_h18p/ (b1 retained) 17 days ago
README.md

16.2 kB
gen-cards: regenerate Use-it block 8 days ago
config.json

306 Bytes
Add root config.json (Hub download-stats query file + framework pointer) about 2 months ago