Christian Medina
|
52b93837f9
|
fix: use NF4 naming convention for quantized model
|
2026-07-02 22:00:15 -04:00 |
|
Christian Medina
|
04a95f362f
|
fix: load bf16 model directly with BnB 4-bit (single load)
|
2026-07-02 21:09:54 -04:00 |
|
Christian Medina
|
57b169f202
|
feat: use BnB 4-bit model for QLoRA training
|
2026-07-02 20:04:55 -04:00 |
|
Christian Medina
|
3c31e4dfb0
|
feat: load bf16 model, quantize with BnB on CPU, move to GPU
|
2026-07-02 19:55:01 -04:00 |
|
Christian Medina
|
5a84b0eee5
|
feat: add CPU offload for optimizer states
|
2026-07-02 17:53:56 -04:00 |
|
Christian Medina
|
a51a744d7c
|
fix: reduce seq_length to 512 and increase gradient_accumulation
|
2026-07-02 17:53:11 -04:00 |
|
Christian Medina
|
691e5d3611
|
feat: use 8-bit AdamW optimizer to save VRAM
|
2026-07-02 17:53:05 -04:00 |
|
Christian Medina
|
0456d55c8a
|
fix: disable gradient checkpointing (device mismatch with distributed MoE)
|
2026-07-02 17:29:19 -04:00 |
|
Christian Medina
|
d9c3781242
|
fix: quote 'no' in eval_strategy (YAML boolean issue)
|
2026-07-02 17:09:40 -04:00 |
|
Christian Medina
|
565ddd416e
|
fix: disable eval (no test split in dataset)
|
2026-07-02 16:49:34 -04:00 |
|
Christian Medina
|
728073ef6a
|
fix: use 'output' column (not 'text')
|
2026-07-02 16:14:53 -04:00 |
|
Christian Medina
|
0752c03b83
|
fix: use absolute path for dataset (no ~ expansion)
|
2026-07-02 16:04:21 -04:00 |
|
Christian Medina
|
b8214f64cb
|
fix: use 4-bit model, remove DeepSpeed, fix dataset path
|
2026-07-02 15:23:26 -04:00 |
|
Christian Medina
|
8747111671
|
fix: update config comment to reflect Ornith-35B
|
2026-07-02 00:11:10 -04:00 |
|
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 |
|