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
{
"templates": {
"audio": "audio.yaml",
"bco": "bco.yaml",
"chat": "chat.yaml",
"code": "code.yaml",
"embedding": "embedding.yaml",
"eu-ai-act": "eu-ai-act.yaml",
"hipaa": "hipaa.yaml",
"ipo": "ipo.yaml",
"kto": "kto.yaml",
"longcontext": "longcontext.yaml",
"medical": "medical.yaml",
"moe": "moe.yaml",
"orpo": "orpo.yaml",
"pretrain": "pretrain.yaml",
"reasoning": "reasoning.yaml",
"rlhf": "rlhf.yaml",
"simpo": "simpo.yaml",
"soc2": "soc2.yaml",
"sr-11-7": "sr-11-7.yaml",
"tool-calling": "tool-calling.yaml",
"vision": "vision.yaml"
},
"version": 1
}