Team Ai
Modelpublic

PeytonT/pdf-tokenization

sourceHugging Faceupdated 3mo agoView on Hugging Face
0likes13downloads
Model Card

PDF Tokenization

Normalizes and models structured PDF-derived paper content for downstream paper tasks.

Model Details

  • —Artifact type: LoRA adapter
  • —Base model: google/flan-t5-base
  • —Backbone type: encoder_decoder
  • —Model ID: P0
  • —Tier: T3_pdf
  • —Role in stack: full-paper or structured-PDF component

This model is part of the Repository Library stack, a research system for indexing, retrieving, aligning, and reasoning over scientific papers, structured paper content, repositories, and cross-domain links between them.

Model Sources

  • —Hugging Face repo: https://huggingface.co/PeytonT/pdf-tokenization
  • —Hugging Face collection: https://huggingface.co/collections/PeytonT/research-library-6a49c589ef4d763f7539b50d
  • —GitHub repository: https://github.com/peytontolbert/research_library
  • —Experiment config: https://github.com/peytontolbert/research_library/blob/main/models/experiments/p0_pdf_tokenization.json
  • —Models directory: https://github.com/peytontolbert/research_library/tree/main/models

Intended Use

  • —Primary use: Normalizes and models structured PDF-derived paper content for downstream paper tasks.
  • —Downstream use: retrieval, ranking, planning, paper understanding, or cross-domain reasoning inside the broader Repository Library system, depending on the model family.
  • —Out of scope: production safety claims, benchmark claims beyond the tracked experiment config, or deployment without task-specific validation.

Training Data

The training inputs for this package were assembled from the following Repository Library data sources:

  • —Source arxiv_pdfs: raw arXiv PDF documents routed through the Repository Library paper pipeline.

Training Procedure

  • —Sources: arxiv_pdfs
  • —Input fields: raw_pdf
  • —Target fields: structured_tokens
  • —Train/val/test split: [0.9, 0.1, 0.0]
  • —Max samples: 4000
  • —Batch size: 2
  • —Precision: bf16
  • —Objective: cross_entropy
  • —Learning rate: 5e-05
  • —Max source tokens: 512
  • —Max target tokens: 256
  • —Fine-tune strategy: peft_lora
  • —Max steps: 1000

Compute

  • —Hardware: 4x RTX_3090 (24 GB)
  • —Distributed strategy: ddp
  • —Estimated GPU hours in config: 0

Evaluation

  • —Declared metrics: perplexity
  • —Status: this card reflects the current tracked experiment configuration and packaged weights in the Repository Library model stack.

Usage

python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel

repo_id = "PeytonT/pdf-tokenization"
base_id = "google/flan-t5-base"

tokenizer = AutoTokenizer.from_pretrained(repo_id)
base = AutoModelForSeq2SeqLM.from_pretrained(base_id)
model = PeftModel.from_pretrained(base, repo_id)

Limitations

  • —These cards are generated from tracked experiment metadata and packaged artifacts, not from a separate benchmark report or external audit.
  • —Several training sources are pipeline outputs from the Repository Library codebase rather than standalone public datasets.
  • —These models are components of a larger research system and should be validated in their target workflow before deployment.

Project Context

  • —GitHub repository: https://github.com/peytontolbert/research_library
  • —Model collection: https://huggingface.co/collections/PeytonT/research-library-6a49c589ef4d763f7539b50d
  • —Publisher: PeytonT