Modelpublic

BirdToast/qwen-attn-lora

sourceHugging Faceupdated 7mo agoView on Hugging Face

0likes8downloads

Model Card

output

This model is a fine-tuned version of rpDungeon/Qwen3-32B-Instruct-TextOnly.

Training procedure

Framework versions

—PEFT 0.18.1
—Loft: 0.1.0
—Transformers: 4.57.3
—Pytorch: 2.9.1
—Datasets: 4.5.0
—Tokenizers: 0.22.2