ViuAI
/

Viu-1.5B-MoE

Text Generation

Mixture of Experts

mixture-of-experts

Model card Files Files and versions

Viu-1.5B-MoE / scratch

3.12 kB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

ViuAI's picture

Fix CUDA OOM on T4: cast model to amp_dtype directly, batch_size=2, safe RMSNorm

41a0763 verified 10 days ago

sync_model_repos.py

3.12 kB
Fix CUDA OOM on T4: cast model to amp_dtype directly, batch_size=2, safe RMSNorm 10 days ago