Instructions to use arnavgrg/codealpaca-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arnavgrg/codealpaca-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "arnavgrg/codealpaca-qlora") - Notebooks
- Google Colab
- Kaggle
How to use the model section in model card.
#4
by sudhir2016 - opened
This looks incorrect. There is no option to load meta-llama/Llama-2-7b-hf in 4bits. Please suggest.
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf", load_in_4bit=True)
Hey, I came across your CodeAlpaca QLoRA model for code generation and found the use case interesting.
I’m exploring how developers are adapting LLMs for specific tasks. Are you happy with the results so far, or are you planning to improve the model further?