YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

texformer-100m-fp16

This repository contains a TeXformer 100m checkpoint in fp16 precision for OCR-to-LaTeX generation.

This is a custom TeXformer architecture checkpoint (model.pt) plus tokenizer assets. It is not a standard transformers AutoModel checkpoint. This export is derived from a checkpoint trained in bf16.

Files

model.pt: TeXformer checkpoint
tokenizer/pdf_tokenizer.json: PDF-side tokenizer
tokenizer/latex_tokenizer.json: LaTeX-side tokenizer
tokenizer/pdf_tags.json: frequent PDF tag metadata
tokenizer/latex_commands.json: frequent LaTeX command metadata

Architecture

Parameters (deduplicated): 96,354,304
Parameters (state_dict entries): 120,930,304
Encoder layers: 6
Decoder layers: 6
Hidden size (d_model): 512
Attention heads: 8
Feed-forward size (d_ff): 2304
Max encoder length: 2560
Max decoder length: 2560
Stored precision: fp16

Quantization

Quantization method: fp16
Checkpoint payload key: model_state_dict
Original model training precision: bf16
Sample tensor dtype: torch.float16

Usage

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-100m-fp16"
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.

Downloads last month: -; Downloads are not tracked for this model. How to track