---
license: other
datasets:
- Gryphe/CoEdit-Alpaca
language:
- en
---
A full finetune of Llama 2 7B using my [Alpaca-transformed CoEdIT dataset](https://huggingface.co/datasets/Gryphe/CoEdit-Alpaca). I gave it three epochs of training using a single A100 80GB GPU.

## Prompt Format

```
### Instruction:
Remove all grammatical errors from this text: <insert text here>

### Response:

```