|
Download README.md from winterdewdev/anlp-a3: direct link, hf CLI and curl.
- Browser
- Download file 2.44 kB
-
https://huggingface.co/winterdewdev/anlp-a3/resolve/main/README.md
- Command line
-
hf download hf://winterdewdev/anlp-a3/README.md
-
curl -L -o README.md https://huggingface.co/winterdewdev/anlp-a3/resolve/main/README.md
2.44 kB
| library_name: pytorch | |
| license: mit | |
| tags: | |
| - pytorch | |
| - mamba | |
| - deltanet | |
| - transformer | |
| - graph-neural-network | |
| - cipher | |
| # ANLP Assignment 3 checkpoints | |
| Checkpoints for both parts of ANLP Assignment 3 (IIIT Hyderabad, 2026). All models are implemented from scratch in PyTorch. Each file holds the model weights and the full training config, and is loaded by the assignment's code. | |
| ## Part 1: cipher decryption | |
| Character-level models that decrypt a position- and context-dependent substitution cipher. The input at step `i` is `embed(p_{i-1}) + embed(c_i)` plus a sinusoidal encoding of the position in the line, and decoding is greedy. Each checkpoint is the best validation-loss checkpoint (step 50,000) of a 50k-step run with a mixed length curriculum. | |
| | File | Model | Parameters | Char acc | Word acc | Norm. Levenshtein | Exact lines | | |
| |---|---|---|---|---|---|---| | |
| | `hybrid/best.pt` (default) | Interleaved `MMDMMDMMDMMD` Mamba / DeltaNet | 6.98M | 9.60% | 3.44% | 0.3783 | 535 / 1318 | | |
| | `transformer/best.pt` | Decoder-only transformer, 8 layers, d 256 | 8.44M | 9.87% | 3.19% | 0.3757 | 529 / 1318 | | |
| | `mamba/best.pt` | Mamba, 16 layers, d 256, d_state 16 | 7.06M | 9.71% | 3.52% | 0.3755 | 524 / 1318 | | |
| | `deltanet/best.pt` | DeltaNet, 8 layers, 4 heads, β ∈ (0, 1) | 6.90M | 9.76% | 3.43% | 0.3755 | 525 / 1318 | | |
| Test-set results (1,318 lines). | |
| ```bash | |
| bash scripts/part1/test_assn.sh --heldout | |
| bash scripts/part1/test_assn.sh --heldout --model transformer | |
| ``` | |
| ## Part 2: fake news detection on UPFD GossipCop | |
| Graph classifiers on news propagation trees. Files are `part2/{model}_{feature}_s{seed}.pt` for seeds 0–4, each the best validation-F1 epoch of a 100-epoch run. | |
| | Model | Features | Parameters | Test F1 (mean ± std, 5 seeds) | | |
| |---|---|---|---| | |
| | Root-only MLP | bert | 115,202 | 0.7286 ± 0.0031 | | |
| | GCN | bert | 246,530 | 0.9693 ± 0.0022 | | |
| | GraphSAGE | bert | 361,218 | 0.9637 ± 0.0023 | | |
| | GAT | bert | 247,042 | 0.9670 ± 0.0024 | | |
| | Bi-GCN | bert | 492,418 | 0.9570 ± 0.0012 | | |
| | GraphSAGE | profile | 70,146 | 0.9628 ± 0.0014 | | |
| | GraphSAGE | spacy | 181,506 | 0.9621 ± 0.0019 | | |
| | GraphSAGE | content | 185,346 | 0.9737 ± 0.0026 | | |
| ```bash | |
| bash scripts/part2/test_gnn.sh --ta | |
| ``` | |
| ## Training logs | |
| WandB: [Part 1](https://forge.coreweave.com/wandb/winterdew-iiit-hyderabad/anlp-a3-part1), [Part 2](https://forge.coreweave.com/wandb/winterdew-iiit-hyderabad/anlp-a3-part2) | |