Instructions to use CMU-AIR2/code-lora-hard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use CMU-AIR2/code-lora-hard with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-1.3b-instruct") model = PeftModel.from_pretrained(base_model, "CMU-AIR2/code-lora-hard") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from CMU-AIR2/code-lora-hard: direct link, hf CLI and curl.
- Browser
- Download file 60.5 MB
-
https://huggingface.co/CMU-AIR2/code-lora-hard/resolve/main/optimizer.pt
- Command line
-
hf download hf://CMU-AIR2/code-lora-hard/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/CMU-AIR2/code-lora-hard/resolve/main/optimizer.pt
60.5 MB
- Xet hash:
- b6b25aa04753572b541b425d194cba719472723e4668ad2e4c7dec43acffc3b5
- Size of remote file:
- 60.5 MB
- SHA256:
- 53ca37dd1e0d69c8cacb4d1b629c9e3087a8f3de78e4f8fd3a01f85a4539a1a1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.