Instructions to use EmTpro01/CodeLlama-7b-java-peft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use EmTpro01/CodeLlama-7b-java-peft with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("EmTpro01/CodeLlama-7b-java-peft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download adapter_model.safetensors from EmTpro01/CodeLlama-7b-java-peft: direct link, hf CLI and curl.
- Browser
- Download file 160 MB
-
https://huggingface.co/EmTpro01/CodeLlama-7b-java-peft/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://EmTpro01/CodeLlama-7b-java-peft/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/EmTpro01/CodeLlama-7b-java-peft/resolve/main/adapter_model.safetensors
160 MB
- Xet hash:
- 21a4013c3babbd1d19ce2548081915de83619deca19a4251cfac88d58f2e6354
- Size of remote file:
- 160 MB
- SHA256:
- 6ab28e78fc88c1d0979f5b7c3b1460cbb58aa518ec1817ab276f5ca9dfbbc9bd
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.