Instructions to use dfurman/Llama-2-70B-Instruct-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use dfurman/Llama-2-70B-Instruct-v0.1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-70b-hf") model = PeftModel.from_pretrained(base_model, "dfurman/Llama-2-70B-Instruct-v0.1") - Notebooks
- Google Colab
- Kaggle
Download assets/basic_inference_llama_2_dolphin.ipynb from dfurman/Llama-2-70B-Instruct-v0.1: direct link, hf CLI and curl.
- Browser
- Download file 39.3 kB
-
https://huggingface.co/dfurman/Llama-2-70B-Instruct-v0.1/resolve/main/assets/basic_inference_llama_2_dolphin.ipynb
- Command line
-
hf download hf://dfurman/Llama-2-70B-Instruct-v0.1/assets/basic_inference_llama_2_dolphin.ipynb
-
curl -L -o basic_inference_llama_2_dolphin.ipynb https://huggingface.co/dfurman/Llama-2-70B-Instruct-v0.1/resolve/main/assets/basic_inference_llama_2_dolphin.ipynb
39.3 kB