buelfhood/SOCO_Adapter_Java_LoRA_0

Adapter buelfhood/SOCO_Adapter_Java_LoRA for huggingface/CodeBERTa-small-v1

An adapter for the huggingface/CodeBERTa-small-v1 model that was trained on the SOCO dataset and includes a prediction head for classification.

This adapter was created for usage with the Adapters library.

Usage

First, install adapters:

pip install -U adapters

Now, the adapter can be loaded and activated like this:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("huggingface/CodeBERTa-small-v1")
adapter_name = model.load_adapter("buelfhood/SOCO_Adapter_Java_LoRA", source="hf", set_active=True)

Architecture & Training

max_length=256 learning_rate=5e-4 epochs=10 batch_size=30 LoRAConfig(r=8, alpha=8)

Architecture & Training

Evaluation results

Citation