|
--- |
|
language: |
|
- en |
|
tags: |
|
- pytorch |
|
- causal-lm |
|
- pythia |
|
license: apache-2.0 |
|
datasets: |
|
- bigbio/med_qa |
|
--- |
|
|
|
This adapter was lora-trained using [lit-gpt](https://github.com/Lightning-AI/lit-gpt) for 12,000 steps (approx. 1 epoch) using [Pythia-410M-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) model on [Med_qa](https://huggingface.co/datasets/bigbio/med_qa) english dataset. |
|
|
|
## Prompt template: |
|
|
|
``` |
|
Below is an Question that is a medical problem, paired with an input that provides the answer choices. Write a response that accurately answers the question. |
|
|
|
### Question: |
|
[QUESTION] |
|
|
|
### Options: |
|
[OPTIONS] |
|
|
|
### Response: |
|
``` |
|
The options is a string like "A. Option 1\nB. Option B\nC. Option C" |
