Instructions to use Anwaarma/edos_taskA_llama_allyears_lora2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Anwaarma/edos_taskA_llama_allyears_lora2 with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Llama-3.2-1B") model = PeftModel.from_pretrained(base_model, "Anwaarma/edos_taskA_llama_allyears_lora2") - Transformers
How to use Anwaarma/edos_taskA_llama_allyears_lora2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Anwaarma/edos_taskA_llama_allyears_lora2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- b7f23082ac121c1172a36e785c138ad337d350faa05d6f07e27c2da22bc24f9e
- Size of remote file:
- 17.2 MB
- SHA256:
- c6eeb16665ec244ff3c2ef4dca42e4cfdcbc7162835201919175747a633511cb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.