Instructions to use answerdotai/ModernBERT-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use answerdotai/ModernBERT-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="answerdotai/ModernBERT-large")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("answerdotai/ModernBERT-large") model = AutoModelForMaskedLM.from_pretrained("answerdotai/ModernBERT-large") - Notebooks
- Google Colab
- Kaggle
Bump `max_position_embeddings` to 8192
Browse filesalso harmonize `layer_norm_eps` with `norm_eps` although the former isn't used
- config.json +2 -2
config.json
CHANGED
|
@@ -23,10 +23,10 @@
|
|
| 23 |
"initializer_cutoff_factor": 2.0,
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
"intermediate_size": 2624,
|
| 26 |
-
"layer_norm_eps": 1e-
|
| 27 |
"local_attention": 128,
|
| 28 |
"local_rope_theta": 10000.0,
|
| 29 |
-
"max_position_embeddings":
|
| 30 |
"mlp_bias": false,
|
| 31 |
"mlp_dropout": 0.0,
|
| 32 |
"model_type": "modernbert",
|
|
|
|
| 23 |
"initializer_cutoff_factor": 2.0,
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
"intermediate_size": 2624,
|
| 26 |
+
"layer_norm_eps": 1e-5,
|
| 27 |
"local_attention": 128,
|
| 28 |
"local_rope_theta": 10000.0,
|
| 29 |
+
"max_position_embeddings": 8192,
|
| 30 |
"mlp_bias": false,
|
| 31 |
"mlp_dropout": 0.0,
|
| 32 |
"model_type": "modernbert",
|