ANLP Assignment 1 - C1 baseline

Custom encoder-decoder Transformer using sinusoidal positions, multi-head attention, pre-LayerNorm and from-scratch byte-level BPE subword tokenization.

Greedy test metrics

bit_accuracy: 0.596782
sequence_accuracy: 0.000000
levenshtein_distance: 469.238000
bleu: 0.568477
rouge1: 0.185158
rouge2: 0.025190
rougeL: 0.146625
parameters: 11841512.000000
best_validation_loss: 2.559813

Load best_model.pt with the architecture and tokenizers from this assignment code.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support