Instructions to use Mishamq/HybriDNA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mishamq/HybriDNA-7B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Mishamq/HybriDNA-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update max sequence length to 131,074 bp
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ HybriDNA combines the efficiency of Mamba state space models with the expressive
|
|
| 28 |
- **Key-Value Heads**: 8 (Grouped Query Attention)
|
| 29 |
- **Mamba Version**: Mamba-2
|
| 30 |
- **Vocabulary**: 12 tokens (A, C, G, T, N + special tokens)
|
| 31 |
-
- **Max Sequence Length**: 131,
|
| 32 |
|
| 33 |
## Installation
|
| 34 |
|
|
|
|
| 28 |
- **Key-Value Heads**: 8 (Grouped Query Attention)
|
| 29 |
- **Mamba Version**: Mamba-2
|
| 30 |
- **Vocabulary**: 12 tokens (A, C, G, T, N + special tokens)
|
| 31 |
+
- **Max Sequence Length**: 131,074 bp
|
| 32 |
|
| 33 |
## Installation
|
| 34 |
|