| --- |
| license: openrail |
| --- |
| |
| --- |
| license: openrail |
| pipeline_tag: text-generation |
| --- |
| |
| **To use MathT5 easily:** |
| |
| 1. Download ```MathT5.py```. |
| 2. ```from MathT5 import load_model, inference``` |
| 3. ```tokenizer, model = load_model("jmeadows17/MathT5-base")``` |
| 4. ```inference(prompt, tokenizer, model)``` |
| |
| ```MathT5.pretty_print(text, prompt=True)``` makes prompts and outputs (```prompt=False```) easier to read. |
| |
| **Overview** |
| |
| MathT5-base is a version of T5-base (_not FLAN-T5_) that is fine-tuned for 25 epochs on 15K (LaTeX) synthetic mathematical derivations (containing 4 - 10 equations), that were generated using a symbolic solver (SymPy). Paper available here: https://arxiv.org/abs/2307.09998. |
| |
| |
| **Example prompt:** |
| |
| ```prompt = "Given \\cos{(q)} = \\theta{(q)}, |
| then derive - \\sin{(q)} = \\frac{d}{d q} \\theta{(q)}, |
| then obtain (- \\sin{(q)})^{q} (\\frac{d}{d q} \\cos{(q)})^{q} = (- \\sin{(q)})^{2 q}"``` |
| |
| Output derivations are equations separated by "and". |
| |
| Additional prompts can be found in "training_prompts.json" alongside the model files. |
| |
| For the large version based on FLAN-T5 use ```"jmeadows17/MathT5-large"```. |
