---
license: other
datasets:
- tatsu-lab/alpaca
---
# Model Card for phi-2-alpaca

This is a low-rank adapter for [phi-2](https://huggingface.co/microsoft/phi-2) fit on the [alpaca](https://huggingface.co/datasets/tatsu-lab/alpaca) dataset.

## Training Hyperparameters

The model was trained on 1xA100 GPU using PEFT-LORA.

The following hyperparameters were used during training:

- Lora target modules: Wqkv, out_proj
- Lora r: 16
- lora_alpha: 16
- lora_dropout: 0.1
- learning_rate: 5e-05
- per_device_train_batch_size: 1
- gradient_accumulation_steps: 1
- training_steps: 120000

## Limitations and Bias

The model is based on a large and diverse dataset, but it may still have limitations and biases in certain areas. Some limitations include:

- Language: The model is designed to work with English text only and may not perform as well in other languages.

In addition, the model may have some bias in terms of the data it was trained on. The dataset includes questions from a variety of sources, but it may not be representative of all populations or perspectives. As a result, the model may perform better or worse for certain types of questions or on certain types of texts.