Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ tokenization_parameters = {
|
|
| 22 |
}
|
| 23 |
# Initialize the tokenizer and model
|
| 24 |
tokenizer = ProkBERTTokenizer(tokenization_params=tokenization_parameters, operation_space='sequence')
|
| 25 |
-
model = MegatronBertForMaskedLM.from_pretrained("nerualbioinfo/prokbert-mini-
|
| 26 |
# Example DNA sequence
|
| 27 |
sequence = 'ATGTCCGCGGGACCT'
|
| 28 |
# Tokenize the sequence
|
|
@@ -52,6 +52,11 @@ outputs = model(**inputs)
|
|
| 52 |
| Layers | 6 |
|
| 53 |
| Attention Heads | 6 |
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
## Segmentation and Tokenization in ProkBERT Models
|
| 57 |
|
|
|
|
| 22 |
}
|
| 23 |
# Initialize the tokenizer and model
|
| 24 |
tokenizer = ProkBERTTokenizer(tokenization_params=tokenization_parameters, operation_space='sequence')
|
| 25 |
+
model = MegatronBertForMaskedLM.from_pretrained("nerualbioinfo/prokbert-mini-k6s1")
|
| 26 |
# Example DNA sequence
|
| 27 |
sequence = 'ATGTCCGCGGGACCT'
|
| 28 |
# Tokenize the sequence
|
|
|
|
| 52 |
| Layers | 6 |
|
| 53 |
| Attention Heads | 6 |
|
| 54 |
|
| 55 |
+
### Intended Use
|
| 56 |
+
|
| 57 |
+
**Intended Use Cases:** ProkBERT-mini-k6-s1 is intended for bioinformatics researchers and practitioners focusing on genomic sequence analysis, including:
|
| 58 |
+
- sequence classification tasks
|
| 59 |
+
- Exploration of genomic patterns and features
|
| 60 |
|
| 61 |
## Segmentation and Tokenization in ProkBERT Models
|
| 62 |
|