Instructions to use SpreadSheets600/electra-lora-mcq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SpreadSheets600/electra-lora-mcq with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
ELECTRA-base + LoRA MCQ Adapter
LoRA adapter (r=16, alpha=32) fine-tuned on the Kaggle Science MCQ dataset.
- MAP@3: 0.8849 (5-fold OOF)
- Accuracy: 81.1%
- Task: 5-way multiple-choice option scoring
Used by: SpreadSheets600/smart-mcq-solver
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for SpreadSheets600/electra-lora-mcq
Base model
google/electra-base-discriminator