| import reflex as rx | |
| p2 = ''' | |
| # Steps | |
| ### Dataset Selection | |
| We begin with the [layoric/labeled-multiple-choice-explained](https://huggingface.co/datasets/layoric/labeled-multiple-choice-explained) dataset, which includes reasoning provided by GPT-3.5-turbo. reasoning explanations serve as a starting point but may differ from Mistral's reasoning style. | |
| 0. *[00-poe-generate-mistral-reasoning.ipynb](https://huggingface.co/derek-thomas/prompt-order-experiment/blob/main/00-poe-generate-mistral-reasoning.ipynb)*: To align with Mistral, we need to create a refined dataset: [derek-thomas/labeled-multiple-choice-explained-mistral-reasoning](https://huggingface.co/datasets/derek-thomas/labeled-multiple-choice-explained-mistral-reasoning). | |
| 1. *[01-poe-dataset-creation.ipynb](https://huggingface.co/derek-thomas/prompt-order-experiment/blob/main/01-poe-dataset-creation.ipynb)*: Then we need to create our prompt experiments. | |
| 2. *[02-autotrain.ipynb](https://huggingface.co/derek-thomas/prompt-order-experiment/blob/main/02-autotrain.ipynb)*: We generate autotrain jobs on spaces to train our models. | |
| 3. *[03-poe-token-count-exploration.ipynb](https://huggingface.co/derek-thomas/prompt-order-experiment/blob/main/03-poe-token-count-exploration.ipynb)*: We do some quick analysis so we can optimize our TGI settings. | |
| 4. *[04-poe-eval.ipynb](https://huggingface.co/derek-thomas/prompt-order-experiment/blob/main/04-poe-eval.ipynb)*: We finally evaluate our trained models. | |
| **The flowchart is _Clickable_** | |
| ''' | |
| def mermaid_svg(): | |
| with open('assets/prompt-order-experiment.svg', 'r') as file: | |
| svg_content = file.read() | |
| return rx.html( | |
| f'<div style="width: 300%; height: auto;">{svg_content}</div>' | |
| ) | |
| def page(): | |
| return rx.vstack( | |
| rx.markdown(p2), | |
| mermaid_svg(), | |
| ) | |