---
base_model: google/flan-t5-base
library_name: peft
pipeline_tag: text2text-generation
tags:
- adapter-fusion
- c5
- repository-library
- research-library
- t5_cross
---

# Adapter Fusion

Fuses paper-conditioned and repo-conditioned adapters into a shared cross-domain component.

## Model Details

- Artifact type: LoRA adapter
- Base model: `google/flan-t5-base`
- Model ID: `C5`
- Tier: `T5_cross`
- Local mirror: `/arxiv/models/repository_library/adapter-fusion`
- Source checkpoint: `models/checkpoints/C5`

This repository is part of the `repository_library` model stack and is mirrored from `/data/repository_library/models/checkpoints` for publication under the `PeytonT` namespace.

## Intended Use

- Primary use: Fuses paper-conditioned and repo-conditioned adapters into a shared cross-domain component.
- Secondary use: retrieval, ranking, planning, or scientific paper tooling inside the broader Repository Library system, depending on the model family.
- Out of scope: production safety claims, benchmark claims beyond the bundled experiment config, or use outside the model's narrow training objective without task-specific validation.

## Training Data

This package was trained from the following declared datasets or corpus sources:

- `source:arxiv_pdfs_structured`
- `source:github_repos`

## Training Procedure

- Sources: `arxiv_pdfs_structured, github_repos`
- Input fields: `paper_adapter, repo_adapter`
- Target fields: `fused_adapter`
- Max samples: `4000`
- Precision: `bf16`
- Objective: `cross_entropy`
- Batch size: `2`
- Learning rate: `5e-05`
- Max source tokens: `512`
- Max target tokens: `256`
- Max steps: `1000`

## Evaluation

- Declared metrics: `perplexity`
- Status: local experiment artifact mirrored for release; external benchmark reporting has not been standardized across the full model family yet.

## Usage

```python
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
from peft import PeftModel

repo_id = "PeytonT/adapter-fusion"
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 model cards reflect the packaged experiment configs and mirrored checkpoint contents, not an independently audited benchmark sheet.
- Some training datasets are local corpora or exported shards, so reproducibility may require access to the surrounding Repository Library data pipeline.
- Models in this stack are narrow components of a larger paper-and-repository system and should be validated on downstream tasks before deployment.

## Project Context

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

## Contact

Published under `PeytonT` from the local `repository_library` build.