README.md

---
license: mit
library_name: transformers
tags:
  - influenza
  - dna
  - genomics
  - antigen
  - language-model
---

# AntigenLM - Influenza Subtype Classifier

Subtype classification head of AntigenLM. Given an `<HA>...<NA>...<sep>` input, predicts one of 12 influenza A subtypes (H1N1, H3N2, H5N1, ...).

Paper: **AntigenLM: Structure-Aware DNA Language Modeling for Influenza** (arXiv:2602.09067).
Code: https://github.com/Moonn1205/AntigenLM  <!-- update with the real repo URL -->

## Usage

```bash
pip install huggingface_hub transformers==4.29.2 torch==1.13.1
```

```python
from huggingface_hub import snapshot_download
snapshot_download(
    repo_id="Moonn1205/AntigenLM-subtype-classifier",
    local_dir="subtype_classifier",
    local_dir_use_symlinks=False,
)
```

Then follow the instructions in the
[code repository](https://github.com/Moonn1205/AntigenLM) to run inference.

## Files

- `pytorch_model.bin`  - model weights
- `config.json`        - GPT-2 backbone config + (classifier only) `label2id` / `id2label`
- `vocab.json`, `tokenizer_config.json`, `special_tokens_map.json` - tokenizer