-
Prune QHexRT HNPU bundle to runtime-minimum artifacts
Remove 5 non-runtime/sensitive files from the QHexRT HNPU bundle.
Strip non-runtime _comment metadata from 2 manifest(s) without changing runtime fields.
Audit artifacts: QHexRT/hf_hnpu_audit cleanup plan, manifest reference check, and multi-agent review.
-
Add chat template block (runtime-owned chat templating)
-
Scrub internal engineering notes from manifest _comment
-
Upload v79/phimoe.json with huggingface_hub
-
Upload v79/ffn_pf.bin with huggingface_hub
-
Upload v79/pf_hi.bin with huggingface_hub
-
Upload v79/pf_lo.bin with huggingface_hub
-
Delete v79/ffndyn.bin with huggingface_hub
-
Upload v79/phimoe.json with huggingface_hub
-
Upload v79/ffn2.bin with huggingface_hub
-
Upload v79/a_hi.bin with huggingface_hub
-
Upload v79/a_lo.bin with huggingface_hub
-
Upload v79/phimoe.json with huggingface_hub
-
Upload v79/a_hi.bin with huggingface_hub
-
Upload v79/a_lo.bin with huggingface_hub
-
Delete v79/embed_table.f32 with huggingface_hub
-
Upload v79/embed_f16.bin with huggingface_hub
-
Upload v79/phimoe.json with huggingface_hub
-
Upload v79/special_tokens_map.json with huggingface_hub
-
Upload v79/tokenizer_config.json with huggingface_hub
-
Upload v79/tokenizer.json with huggingface_hub
-
Upload v79/embed_table.f32 with huggingface_hub
-
Upload v79/experts_scale.f32 with huggingface_hub
-
Upload v79/experts_i8.bin with huggingface_hub
-
Upload v79/lmhead_ar1.bin with huggingface_hub
-
Upload v79/ffndyn.bin with huggingface_hub
-
Upload v79/a_hi.bin with huggingface_hub
-
Upload v79/a_lo.bin with huggingface_hub