Update README.md
Browse files
README.md
CHANGED
|
@@ -23,15 +23,13 @@ NucEL is a specialized language model designed for nucleotide sequence analysis
|
|
| 23 |
|
| 24 |
- **Model Type**: Transformer-based sequence model
|
| 25 |
- **Domain**: Genomics and Nucleotide Sequences
|
| 26 |
-
- **Architecture**: Based on
|
| 27 |
-
- **Tokenizer**: Custom NucEL tokenizer with k=1 for nucleotide-level tokenization
|
| 28 |
|
| 29 |
## Features
|
| 30 |
|
| 31 |
- Nucleotide-level tokenization and embedding
|
| 32 |
-
- Pre-trained on
|
| 33 |
- Optimized for biological sequence understanding
|
| 34 |
-
- Compatible with HuggingFace transformers library
|
| 35 |
|
| 36 |
## Usage
|
| 37 |
|
|
@@ -85,7 +83,3 @@ If you use NucEL in your research, please cite:
|
|
| 85 |
## License
|
| 86 |
|
| 87 |
This model is released under the Apache 2.0 License.
|
| 88 |
-
|
| 89 |
-
## Contact
|
| 90 |
-
|
| 91 |
-
For questions and support, please open an issue in the repository or contact [your-email@example.com].
|
|
|
|
| 23 |
|
| 24 |
- **Model Type**: Transformer-based sequence model
|
| 25 |
- **Domain**: Genomics and Nucleotide Sequences
|
| 26 |
+
- **Architecture**: Based on ModernBert architecture optimized for nucleotide sequences
|
|
|
|
| 27 |
|
| 28 |
## Features
|
| 29 |
|
| 30 |
- Nucleotide-level tokenization and embedding
|
| 31 |
+
- Pre-trained on human genome
|
| 32 |
- Optimized for biological sequence understanding
|
|
|
|
| 33 |
|
| 34 |
## Usage
|
| 35 |
|
|
|
|
| 83 |
## License
|
| 84 |
|
| 85 |
This model is released under the Apache 2.0 License.
|
|
|
|
|
|
|
|
|
|
|
|