Instructions to use Vinceorz/codellama_python_34b_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Vinceorz/codellama_python_34b_v1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-34b-Python-hf") model = PeftModel.from_pretrained(base_model, "Vinceorz/codellama_python_34b_v1") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from Vinceorz/codellama_python_34b_v1: direct link, hf CLI and curl.
- Browser
- Download file 39.4 MB
-
https://huggingface.co/Vinceorz/codellama_python_34b_v1/resolve/main/adapter_model.bin
- Command line
-
hf download hf://Vinceorz/codellama_python_34b_v1/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/Vinceorz/codellama_python_34b_v1/resolve/main/adapter_model.bin
39.4 MB
- Xet hash:
- 6963e3e6162c83f17720b225e6f50aa6817f8bc1d2cc4657366d21cf0515ed8b
- Size of remote file:
- 39.4 MB
- SHA256:
- 0b6253978a624fca741bc6fab20e9a331eb1672c98ec8c17445d57da68ff14d1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.