README.md

---
license: apache-2.0
tags:
- biology
- genomics
- single-cell
library_name: transformers
---

# TXModel - Hub-Ready Version

**Zero-hassle deployment!** Requires ONLY:
```bash
pip install transformers torch safetensors
```

## 🚀 Quick Start

```python
from transformers import AutoModel
import torch

# Load from Hub (one command!)
model = AutoModel.from_pretrained(
    "your-username/model-name",
    trust_remote_code=True
)

# Use immediately
genes = torch.randint(0, 100, (2, 10))
values = torch.rand(2, 10)
masks = torch.ones(2, 10).bool()

model.eval()
with torch.no_grad():
    output = model(genes=genes, values=values, gen_masks=masks)
    
print(output.last_hidden_state.shape)  # [2, 10, d_model]
```

## ✨ Features

- ✅ **Single file** - all code in `modeling.py`
- ✅ **Zero dependencies** (except transformers + torch)
- ✅ **Works with AutoModel** out of the box
- ✅ **No import errors** - everything self-contained

## 📦 Installation

```bash
pip install transformers torch safetensors
```

That's it!

## 🎯 Usage

### Basic Inference

```python
from transformers import AutoModel

model = AutoModel.from_pretrained(
    "your-username/model-name",
    trust_remote_code=True
)

# Move to GPU if available
device = "cuda" if torch.cuda.is_available() else "cpu"
model = model.to(device)
```

### Batch Processing

```python
# Your data
batch = {
    'genes': torch.randint(0, 1000, (32, 100)),
    'values': torch.rand(32, 100),
    'masks': torch.ones(32, 100).bool()
}

# Process
model.eval()
with torch.no_grad():
    output = model(**batch)
```

## 📊 Model Details

- **Parameters**: ~70M
- **Architecture**: Transformer Encoder
- **Hidden Size**: 512
- **Layers**: 12
- **Heads**: 8

## 📝 Citation

```bibtex
@article{tahoe2024,
  title={Tahoe-x1},
  author={...},
  year={2024}
}
```