patdev
/

Companion-Forge-L4-ONNX

Model card Files Files and versions

Companion-Forge-L4-ONNX / v7 /training /fp8_sparse.py

Commit History

Fix v7 ModelOpt FP8 and AutoQuantize API for 2026 release

d0cff17
verified

patdev commited on 2 days ago

Update v7 selective FP8 to current ModelOpt ordered quant_cfg API

9a83119
verified

patdev commited on 2 days ago

Add v7 distillation FP8 sparsity DINOv3 multiview symmetry MoE stack

27fe41c
verified

patdev commited on 2 days ago