Christian Medina 22d1bfd573 fix: use 4-bit model first, then bf16 with CPU offload

2026-07-01 14:43:30 -04:00

..

inference.py

init: add LoRA training infrastructure and 20k dataset

2026-06-30 14:49:44 -04:00

prepare_dataset.py

fix: use output_file parameter in prepare_dataset

2026-06-30 21:54:05 -04:00

run_with_accelerate.sh

feat: add run_with_accelerate.sh helper script

2026-06-30 18:26:08 -04:00

train.py

fix: use 4-bit model first, then bf16 with CPU offload

2026-07-01 14:43:30 -04:00