Downloads · 30 days
0
anlp-a1-c1
shauryakochar/anlp-a1-c1
anlp-a1-c1 is a machine learning model from shauryakochar. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Encoder-decoder Transformer built from basic PyTorch operations (no nn.Transformer, nn.MultiheadAttention or nn.LayerNorm), trained to map encrypted binary sequences to plaintext.
Access
Public
Updated Sep 2, 2026
Repo size
32.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt32.2 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026
- SHA
- 46bac574
Model card
From the Hugging Face model README
ANLP Assignment 1 - C1: base (sinusoidal + MHA + LayerNorm + BPE)
Encoder-decoder Transformer built from basic PyTorch operations (no nn.Transformer,
nn.MultiheadAttention or nn.LayerNorm), trained to map encrypted binary sequences to
plaintext.
Configuration
C1 - base (sinusoidal + MHA + LayerNorm + BPE)
Test metrics (greedy decoding)
{
"config": "C1",
"params": 7767552,
"train_time_s": 3110.2649331092834,
"sec_per_epoch": 44.43235618727548,
"test_bit_accuracy": 0.9937785706907158,
"test_char_accuracy": 0.9844609953794571,
"test_sequence_accuracy": 0.9276248725790011,
"test_levenshtein": 0.12313965341488277,
"test_levenshtein_norm": 0.0020274307350443416,
"test_bleu": 0.9836798436193944,
"test_rouge_l": 0.99181781932517,
"peak_mem_mb": 1336.927744
}
Files
C1.pt- model weights, config and training arguments
Code: https://github.com/shaurya-kochar/anlp-assignment1 WandB: https://wandb.ai/shaurya-kochar-iiit-hyderabad/anlp-a1-transformer-ablation
- License
- mit
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026