VOOZH about

URL: https://huggingface.co/zqmalyssa/Qwen2.5-1.5B-Assistant

⇱ zqmalyssa/Qwen2.5-1.5B-Assistant · Hugging Face


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
Downloads last month
138
Safetensors
Model size
2B params
Tensor type
F16
·

Model tree for zqmalyssa/Qwen2.5-1.5B-Assistant

Quantized
(70)
this model

Datasets used to train zqmalyssa/Qwen2.5-1.5B-Assistant