Downloads · 30 days
0
ANLP-A1-Transformer-Ablations
dhyeythummar9/ANLP-A1-Transformer-Ablations
ANLP-A1-Transformer-Ablations is a machine learning model from dhyeythummar9. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Pretrained checkpoints for five custom encoder-decoder Transformer configurations implemented in PyTorch.
Access
Public
Updated Sep 2, 2026
Repo size
520 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt520 MB · 100%
At a glance
- Access
- Public
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026
- SHA
- 8f709db8
Model card
From the Hugging Face model README
ANLP Assignment 1 — Transformer Ablation Study
Pretrained checkpoints for five custom encoder-decoder Transformer configurations implemented in PyTorch.
Configurations
- C1: Sinusoidal PE + MHA + LayerNorm + BPE
- C2: RoPE + MHA + LayerNorm + BPE
- C3: Sinusoidal PE + GQA + LayerNorm + BPE
- C4: Sinusoidal PE + MHA + RMSNorm + BPE
- C5: Sinusoidal PE + MHA + LayerNorm + BLT
Checkpoints
best_c1_model.ptbest_c2_model.ptbest_c3_model.ptbest_c4_model.ptbest_c5_model.pt
C1-C4 use the included cipher_tokenizer.json and tokenizer.json.
C5 uses the token-free byte-level BLT pipeline.
- Created
- Sep 2, 2026
- Updated
- Sep 2, 2026