Views
No views yet
formulanet.pt from alephpi/FormulaNet): 58M parameter model with HGNetV2 encoder + MBart decoder. This is the distilled checkpoint from the original Texo paper, prior to any UniMER training.| Dataset | m4xi/unimer-merged (~1.04M train samples, 98/2 train/val split) |
| Fine-tune strategy | Full (no LoRA) |
| Effective batch size | 64 (16 per device × 4 grad accum) |
| Learning rate | 1e-4, cosine decay |
| Precision | bf16 |
| Steps | 1,750 (~0.11 epochs, ~112K samples seen) |
| Hardware | NVIDIA RTX 4090, ~42h total runtime (crashed) |
save_top_k=5 retained only the five best-BLEU checkpoints, all of which fell within the first ~15% of epoch 1; consistent with rapid convergence from a strong pretrained base.1import torch
2from task import FormulaNetLit # Texo src/task.py
3
4model = FormulaNetLit.load_from_checkpoint("texo-cp-1750.ckpt", map_location="cpu")
5model.eval()
6
7outputs = model.generate(pixel_values, num_beams=1, do_sample=False, max_new_tokens=512)
8pred = model.tokenizer.batch_decode(outputs, skip_special_tokens=True)