nanochat/dev
William Thurston 8a6d34daf7 Add kv_head_mult parameter for training and evaluation scripts
- Introduced `kv_head_mult` to control the number of query heads sharing a key/value head in `base_train.py`, `mid_train.py`, and `runmps.sh`.
- Updated logging to include global token per second metrics during training.
- Added assertions to ensure `kv_head_mult` is valid and properly integrated into model calculations.
2025-11-09 14:23:45 -08:00
..
gen_synthetic_data.py add personality to nanochat. breaks previous code on git pull and requires download of a new file from s3, but there is a helpful error message so hopefully its ok 2025-10-21 15:04:58 +00:00
generate_logo.html initial commit 2025-10-13 06:49:24 -07:00
nanochat.png add nanochat logo png 2025-10-13 06:59:59 -07:00
repackage_data_reference.py initial commit 2025-10-13 06:49:24 -07:00
runcpu.sh Add scripts for running evaluations and training with W&B integration 2025-11-05 11:49:50 -08:00
runmps_evals.sh Add scripts for running evaluations and training with W&B integration 2025-11-05 11:49:50 -08:00
runmps.sh Add kv_head_mult parameter for training and evaluation scripts 2025-11-09 14:23:45 -08:00