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/paper-qa
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/p5_paper_qa.json
Models directory: https://github.com/peytontolbert/research_library/tree/main/models

Intended Use

Primary use: Answers questions over paper text and structured paper context.
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:

Primary published dataset: local/paper_text_2m_dedup_v1
Source paper_text_parquet: full-text paper corpus records prepared for model training.

Training Procedure

Sources: paper_text_parquet
Input fields: question, paper_context
Target fields: answer
Train/val/test split: [0.8, 0.1, 0.1]
Max samples: 4000
Batch size: 4
Precision: bf16
Objective: cross_entropy
Learning rate: 0.0001
Max source tokens: 512
Max target tokens: 192
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: rougeL, bleu
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/paper-qa"
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