phi4_hmt / README.md

Update README.md

1993411 verified 9 months ago

188 Bytes

license: mit
datasets:
  - HuggingFaceFW/fineweb
  - nvidia/ChatQA2-Long-SFT-data
language:
  - en
base_model:
  - microsoft/phi-4

Pretraining checkpoints for HMT training for Phi-4 model