Hugging Face's logo

MOFI0681
/
lora2026_cpu

Text Generation
PEFT
Safetensors
English
lora
cpu-training
conversational
Model card Files
xet
Community

Qwen2.5-0.5B Structured Output LoRA (CPU)

LoRA adapter fine-tuned from Qwen/Qwen2.5-0.5B-Instruct on CPU.

Training Configuration

  • Epochs: 1
  • Learning rate: 2e-05
  • LoRA r=8, alpha=16
Downloads last month
7
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MOFI0681/lora2026_cpu

Base model

Qwen/Qwen2.5-0.5B
Finetuned
Qwen/Qwen2.5-0.5B-Instruct
Adapter
(414)
this model

Dataset used to train MOFI0681/lora2026_cpu