Greg Hendrickson 39922e8d2e feat: Add Gemma 3 12B with QLoRA fine-tuning ...

- Added PEFT, bitsandbytes, TRL for LoRA training
- 4-bit QLoRA quantization for 48GB GPU fit
- Instruction-tuning format for Gemma chat template
- Auto-detect model type (BERT vs LLM)
- Updated GPU tier to ADA_24/AMPERE_48

2026-02-03 03:58:25 +00:00

..

Dockerfile

Fix Python/transformers version compatibility

2026-02-03 01:11:20 +00:00

handler.py

feat: Add Gemma 3 12B with QLoRA fine-tuning

2026-02-03 03:58:25 +00:00

requirements.txt

feat: Add Gemma 3 12B with QLoRA fine-tuning

2026-02-03 03:58:25 +00:00