Christian Medina
|
815115e97a
|
feat: add BnB 4-bit quantization strategy + use bf16 model
|
2026-07-01 21:14:31 -04:00 |
|
Christian Medina
|
3760aaf316
|
fix: rename output dir to ornith-35b-lora
|
2026-07-01 14:19:43 -04:00 |
|
Christian Medina
|
14042dbb44
|
fix: use pre-quantized 4bit model
|
2026-07-01 12:35:19 -04:00 |
|
Christian Medina
|
2fa5173c56
|
feat: add prepare_model_for_kbit_training and update LoRA r=64 alpha=128
|
2026-07-01 07:48:44 -04:00 |
|
Christian Medina
|
da5eb3abed
|
feat: implement QLoRA with 4-bit BitsAndBytes quantization
|
2026-07-01 07:45:33 -04:00 |
|
Christian Medina
|
f47944ee75
|
fix: remove quantization_config after loading to bypass SFTTrainer check
|
2026-07-01 07:36:38 -04:00 |
|
Christian Medina
|
6f631f00ae
|
fix: use FP8 model with 32GB CPU offload
|
2026-07-01 07:29:32 -04:00 |
|
Christian Medina
|
9d92531c55
|
fix: use Ornith-1.0-35B bf16 base model (PEFT compatible)
|
2026-07-01 07:28:21 -04:00 |
|
Christian Medina
|
8d4cdca3bb
|
feat: use Ornith-1.0-35B-NVFP4 for training
|
2026-06-30 23:34:33 -04:00 |
|
Christian Medina
|
5713bf0285
|
fix: add CPU offload back to DeepSpeed ZeRO-3
|
2026-06-30 22:47:19 -04:00 |
|
Christian Medina
|
a8c9cd682e
|
fix: simplify DeepSpeed config, remove offload settings
|
2026-06-30 22:36:49 -04:00 |
|
Christian Medina
|
6bd6662f5f
|
docs: rename config and docs to reflect Ornith-35B model
|
2026-06-30 20:41:53 -04:00 |
|