22 lines
592 B
Markdown
22 lines
592 B
Markdown
---
|
|
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.
|
|
|
|
The intent was to create a L2 model that specializes in grammar correction. Results may vary.
|
|
|
|
## Prompt Format
|
|
|
|
```
|
|
Below is an instruction that describes a task. Write a response that appropriately completes the request.
|
|
|
|
### Instruction:
|
|
Remove all grammatical errors from this text: <insert text here>
|
|
|
|
### Response:
|
|
|
|
``` |