24 days ago
-
refactor: consolidate pure 32L Dense architecture, purge MoE files, audit hardening
-
Audit fix: Update README.md for ViuMini-Dense-360M
-
Update README.md for ViuMini-Dense-360M 32L architecture
26 days ago
-
Fix CUDA OOM on T4: cast model to amp_dtype directly, batch_size=2, safe RMSNorm
-
sync local: enforce_mix sampler, tokenizer v2 (mask fix + 35/30/35), mix optional docs, repair scripts
-
init: 28L MoE 241M audit-fixed, smoke pass
