algebra_linear_1d

language: en datasets: - algebra_linear_1d

This is a t5-small fine-tuned version on the math_dataset/algebra_linear_1d for solving algebra 1d equations mission.

To load the model: (necessary packages: !pip install transformers sentencepiece)

from transformers import AutoTokenizer, AutoModelWithLMHead
tokenizer = AutoTokenizer.from_pretrained("dbernsohn/algebra_linear_1d")
model = AutoModelWithLMHead.from_pretrained("dbernsohn/algebra_linear_1d")

You can then use this model to solve algebra 1d equations into numbers.

query = "Solve 0 = 1026*x - 2474 + 46592 for x"
input_text = f"{query} </s>"
features = tokenizer([input_text], return_tensors='pt')
model.to('cuda')
output = model.generate(input_ids=features['input_ids'].cuda(), 
                        attention_mask=features['attention_mask'].cuda())

tokenizer.decode(output[0])
# <pad> -41</s>

Another examples:

Solve 1112r + 1418r - 5220 = 587*r - 28536 for r.
Answer: -12 Pred: -12

Solve -119k + 6k - 117 - 352 = 322 for k.
Answer: -7 Pred: -7

Solve -547 = -62*t + 437 - 798 for t.
Answer: 3 Pred: 3

Solve 3j - 3j + 0j - 4802 = 98j for j.
Answer: -49 Pred: -49

Solve 3047n - 6130n - 1700 = -3049*n for n.
Answer: -50 Pred: -50

Solve 121i + 1690 = 76i - 128*i + 133 for i.
Answer: -9 Pred: -9

The whole training process and hyperparameters are in my GitHub repo

Created by Dor Bernsohn