Fill-Mask
Transformers
Safetensors
Upper Grand Valley Dani
bert
DNA
BERT
language-model
genomics
custom_code
Instructions to use Taykhoom/DNABERT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Taykhoom/DNABERT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="Taykhoom/DNABERT2", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("Taykhoom/DNABERT2", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("Taykhoom/DNABERT2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add model_max_length; remove unused max_position_embeddings & position_embedding_type (MosaicBERT uses ALiBi)
Browse files- config.json +0 -2
config.json
CHANGED
|
@@ -18,13 +18,11 @@
|
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 3072,
|
| 20 |
"layer_norm_eps": 1e-12,
|
| 21 |
-
"max_position_embeddings": 512,
|
| 22 |
"model_max_length": 10000,
|
| 23 |
"model_type": "bert",
|
| 24 |
"num_attention_heads": 12,
|
| 25 |
"num_hidden_layers": 12,
|
| 26 |
"pad_token_id": 3,
|
| 27 |
-
"position_embedding_type": "absolute",
|
| 28 |
"transformers_version": "4.57.6",
|
| 29 |
"type_vocab_size": 2,
|
| 30 |
"use_cache": true,
|
|
|
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 3072,
|
| 20 |
"layer_norm_eps": 1e-12,
|
|
|
|
| 21 |
"model_max_length": 10000,
|
| 22 |
"model_type": "bert",
|
| 23 |
"num_attention_heads": 12,
|
| 24 |
"num_hidden_layers": 12,
|
| 25 |
"pad_token_id": 3,
|
|
|
|
| 26 |
"transformers_version": "4.57.6",
|
| 27 |
"type_vocab_size": 2,
|
| 28 |
"use_cache": true,
|