software-mansion
/

react-native-executorch-qwen-3

Text Generation

Model card Files Files and versions

react-native-executorch-qwen-3 / 0_6b

Commit History

update models

738a5fe

bhanc commited on about 2 hours ago

Add MLX int4 variants for 0.6B, 1.7B and 4B

fa72381
verified

msluszniak commited on Sep 5

Stop restating quantized, and drop the unused default

e81de1f

aceOfDiamonds commited on Sep 3

Use min/max dynamic shape bounds for forward inputs/outputs

35163d4

NorbertKlockiewicz commited on Jun 22

Backfill constant metadata method values in config.json from .pte

bbc7a6d

NorbertKlockiewicz commited on Jun 22

Add spec-compliant config.json files

3773abc
verified

msluszniak commited on May 13

Add spec-compliant config.json files

ad1a143
verified

msluszniak commited on May 13

Restructure to MODEL_SPEC.md convention

35ec938
verified

msluszniak commited on May 13