license, datasets, language, metrics, base_model, pipeline_tag, library_name, tags

license	datasets	language	metrics	base_model	pipeline_tag	library_name	tags
apache-2.0	shibing624/alpaca-zh hiyouga/DPO-En-Zh-20k	zh en	accuracy	Qwen/Qwen2.5-1.5B	text-generation	transformers	qwen dpo sft alignment ollama

A lightweight model fine-tuned from Qwen2.5-1.5B via SFT and DPO alignment. Enjoy!

Phase	Metric	Value
SFT	Final Loss	1.65
DPO	Accuracies	70.4%
DPO	Margins	1.022