PEFT
Safetensors
English
Chinese
lora
distillation
svd
cross-architecture
adaptive-rank
gemma
llama
nemotron
Instructions to use win10/Nemotron2Gemma-AURORA-LoRA-27B-IT-0p95 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use win10/Nemotron2Gemma-AURORA-LoRA-27B-IT-0p95 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("E:\text-generation-webui-1.14\user_data\models\google-gemma-3-27b-it-text") model = PeftModel.from_pretrained(base_model, "win10/Nemotron2Gemma-AURORA-LoRA-27B-IT-0p95") - Notebooks
- Google Colab
- Kaggle
Ctrl+K