Instructions to use richardr1126/spider-skeleton-wizard-coder-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use richardr1126/spider-skeleton-wizard-coder-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("WizardLM/WizardCoder-15B-V1.0") model = PeftModel.from_pretrained(base_model, "richardr1126/spider-skeleton-wizard-coder-qlora") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from richardr1126/spider-skeleton-wizard-coder-qlora: direct link, hf CLI and curl.
- Browser
- Download file 442 MB
-
https://huggingface.co/richardr1126/spider-skeleton-wizard-coder-qlora/resolve/refs%2Fpr%2F1/adapter_model.bin
- Command line
-
hf download hf://richardr1126/spider-skeleton-wizard-coder-qlora@refs/pr/1/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/richardr1126/spider-skeleton-wizard-coder-qlora/resolve/refs%2Fpr%2F1/adapter_model.bin
442 MB
- Xet hash:
- 2bdf712ed3d0381577e2f0afa4a843bee067430351d1e7f79cc46fbb7edcf86a
- Size of remote file:
- 442 MB
- SHA256:
- 0d02182a249648e8a2081f5541ceaafde7889a107632ef9849dc77fb371fa5ef
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.