Trained transformer models for predicting traces of Frobenius of elliptic curves with conductor up to 10^6

Trained transformer models for predicting traces of Frobenius $a_p(E)$ of elliptic curves $E$ with conductor up to $10^6$ and good reduction at $p$ for $p \in \{2, 3, 97\}$. The input consists of sequences $(a_q(E))_{q < 100, q \ne p}$.  The models were trained using Int2Int, and the training and test sets were created from the datasets Frobenius traces of small primes for a subset of isogeny classes of elliptic curves of conductor up to 10^6  and Frobenious traces for a set of isogeny classes of elliptic curves of conductor up to 10^6. The code for generating these datasets, and training and loading the models can be found in LearningEulerFactors, and a discussion of the results in Learning Euler Factors of Elliptic Curves.