---
library_name: transformers
license: apache-2.0
datasets:
- tasksource/ScienceQA_text_only
base_model:
  - 01-ai/Yi-1.5-9B-Chat
---

# yi-wissenschaft-9B

[01-ai/Yi-1.5-9B-Chat](https://huggingface.co/01-ai/Yi-1.5-9B-Chat) finetuned on [tasksource/ScienceQA_text_only](https://huggingface.co/datasets/tasksource/ScienceQA_text_only).

### Method

Finetuned using an A100 on Google Colab. Correct answers were selected as the chosen answer, a random wrong answer was selected as "rejected."

[Fine-Tune Your Own Llama 2 Model in a Colab Notebook](https://mlabonne.github.io/blog/posts/Fine_Tune_Your_Own_Llama_2_Model_in_a_Colab_Notebook.html)