from pathlib import Path
import torch
from huggingface_hub import snapshot_download
from texformer.models.checkpoint_loader import load_texformer_model
from texformer.tokenization.tokenizer import TeXFormerTokenizer

repo_id = "aamingem/texformer-576m-bf16"
local_dir = Path(snapshot_download(repo_id=repo_id))
tokenizer_dir = local_dir / "tokenizer"

tokenizer = TeXFormerTokenizer(tokenizer_dir)
if torch.cuda.is_available():
    device = torch.device("cuda")
elif hasattr(torch.backends, "mps") and torch.backends.mps.is_available():
    device = torch.device("mps")
else:
    device = torch.device("cpu")
model, global_step, epoch, missing, unexpected = load_texformer_model(
    checkpoint_path=local_dir / "model.pt",
    tokenizer=tokenizer,
    device=device,
)
print("Loaded model:", model.__class__.__name__)
print("Missing keys:", len(missing), "Unexpected keys:", len(unexpected))

Intended Use

OCR-to-LaTeX / PDF-text-to-LaTeX sequence generation
Research and experimentation on scientific document conversion

Limitations

May produce incorrect or non-compiling LaTeX.
Performance depends on input extraction quality.
Not intended for high-stakes use without human verification.