Instructions to use chambul/MediSimplifier-LoRA-Adapter-Nebius with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use chambul/MediSimplifier-LoRA-Adapter-Nebius with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("aaditya/Llama3-OpenBioLLM-8B") model = PeftModel.from_pretrained(base_model, "chambul/MediSimplifier-LoRA-Adapter-Nebius") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 9932e04b51814e2a68a6876c62d336f6459d02ed7b368ec9f5442a98d80d7323
- Size of remote file:
- 17.2 MB
- SHA256:
- cd0b191129ffe6d570f40eb6896291e891b029a08b909f8ddae3b39f589f170c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.