README.md

---
license: cc-by-nc-4.0
library_name: transformers
tags:
- nv-embed
- embedding
- retrieval
- transformers
base_model: nvidia/NV-Embed-v2
---

# NV-Embed-v2 (Migrated for transformers 5.0+ compatibility)

This is a migrated version of [nvidia/NV-Embed-v2](https://huggingface.co/nvidia/NV-Embed-v2) that is compatible with transformers 5.0.0 and later versions.

## Changes from Original

The only change made is adding an `all_tied_weights_keys` property to the `NVEmbedModel` class in `modeling_nvembed.py`. This property provides backward compatibility with the transformers library, which changed from using `_tied_weights_keys` (a class attribute) to `all_tied_weights_keys` (a property that returns a dict) in version 5.0.0.

### The Patch

```python
@property
def all_tied_weights_keys(self):
    """Compatibility property for transformers >= 5.0.0."""
    if hasattr(self, '_tied_weights_keys') and self._tied_weights_keys:
        return {key: key for key in self._tied_weights_keys}
    return {}
```

## Usage

```python
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Hyukkyu/nv-embed-v2", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("Hyukkyu/nv-embed-v2", trust_remote_code=True)
```

## Original Model

This model is based on [nvidia/NV-Embed-v2](https://huggingface.co/nvidia/NV-Embed-v2). Please refer to the original repository for:
- Model architecture details
- Training information
- Benchmarks and evaluation results
- Citation information

## License

This model inherits the license from the original repository. Please check [nvidia/NV-Embed-v2](https://huggingface.co/nvidia/NV-Embed-v2) for license details.

## Migration Tool

This model was migrated using the GenZ model migration tool. The migration script is available at:
https://github.com/your-repo/GenZ/tree/main/scripts/preprocess/model

## Compatibility

- **transformers**: >= 5.0.0
- **torch**: >= 2.0.0
- **Python**: >= 3.9