Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Python cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llmloralow-vrammachine-learningollamapeftpythonpytorchqlorasfttransformers
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| _fixtures | ||
| providers | ||
| templates | ||
| traces | ||
| __init__.py 0 B | ||
| augment.py 5.9 KB | ||
| chat_templates.py 5.5 KB | ||
| collators.py 5.0 KB | ||
| formats.py 50.1 KB | ||
| loader.py 69.3 KB | ||
| loss_mask.py 28.0 KB | ||
| sft_format.py 9.8 KB | ||
| validator.py 8.4 KB | ||