Modelpublic

legoskier/Qwen2.5-7B-distillation-lora_3_1

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes

2 commits on main

ef175ab7mo ago

Upload A100-optimized merged Qwen3-4B model (ALFWorld+DBBench, seq=8192, LoRA r=256)

legoskier

1c207fb7mo ago

initial commit

legoskier