Go to file

Jiarui Li cb7575a229 feat: Update model and training parameters

In `models.py`:
- Change temporal attention mask to be strictly causal (`<` instead of `<=`).
- Add self-attention for the first token in a sequence to prevent NaNs.

In `train.py`:
- Update hyperparameters:
  - `block_length`: 24 -> 48
  - `n_embd`: 256 -> 120
  - `n_layer`: 8 -> 12
  - `n_head`: 8 -> 12

2025-10-16 18:50:15 +08:00

.gitattributes

feat: Add training and validation data via Git LFS

2025-10-16 14:24:56 +08:00

GEMINI.md

feat: Implement time-aware GPT-2 for patient event prediction

2025-10-16 14:21:36 +08:00

LICENSE

Initial commit

2025-10-15 13:54:52 +08:00

models.py

feat: Update model and training parameters