ANLP Assignment 1: Transformer Ablations

This repository contains the trained weights for a sequence-to-sequence translation task using various custom-built Transformer architectures from scratch.

Checkpoints Included

  • C1_baseline/best.pt: Baseline Transformer (Sinusoidal PE, MHA, LayerNorm)
  • C2_rope/best.pt: Rotary Positional Encoding (RoPE)
  • C3_gqa/best.pt: Grouped-Query Attention (GQA)
  • C4_rmsnorm/best.pt: RMSNorm

Tokenizers

The shared BPE tokenizers used to encode the sequence data are included in the root directory:

  • src_tokenizer.json
  • tgt_tokenizer.json

Author: Rachit Mehta (2024101089)

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