Fill-Mask
Transformers
Safetensors
English
modernbert_small
babylm
babylm-2026
modernbert
masked-language-model
strict-small
custom_code
Instructions to use remg1997/modernbert-small-modernbert-small-factorized-linear-babylm2026 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use remg1997/modernbert-small-modernbert-small-factorized-linear-babylm2026 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="remg1997/modernbert-small-modernbert-small-factorized-linear-babylm2026", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("remg1997/modernbert-small-modernbert-small-factorized-linear-babylm2026", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add missing AutoModel auto_map entry (needed for babylm-eval finetune.run's AutoModel.from_pretrained)
Browse files- config.json +3 -2
config.json
CHANGED
|
@@ -6,7 +6,8 @@
|
|
| 6 |
"attention_pattern": "alternating",
|
| 7 |
"auto_map": {
|
| 8 |
"AutoConfig": "configuration_modernbert_small.ModernBertSmallConfig",
|
| 9 |
-
"AutoModelForMaskedLM": "modeling_modernbert_small.ModernBertSmallForMaskedLM"
|
|
|
|
| 10 |
},
|
| 11 |
"dtype": "float32",
|
| 12 |
"embedding_dropout": 0.0,
|
|
@@ -30,4 +31,4 @@
|
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"transformers_version": "4.57.6",
|
| 32 |
"vocab_size": 30522
|
| 33 |
-
}
|
|
|
|
| 6 |
"attention_pattern": "alternating",
|
| 7 |
"auto_map": {
|
| 8 |
"AutoConfig": "configuration_modernbert_small.ModernBertSmallConfig",
|
| 9 |
+
"AutoModelForMaskedLM": "modeling_modernbert_small.ModernBertSmallForMaskedLM",
|
| 10 |
+
"AutoModel": "modeling_modernbert_small.ModernBertSmallModel"
|
| 11 |
},
|
| 12 |
"dtype": "float32",
|
| 13 |
"embedding_dropout": 0.0,
|
|
|
|
| 31 |
"tie_word_embeddings": false,
|
| 32 |
"transformers_version": "4.57.6",
|
| 33 |
"vocab_size": 30522
|
| 34 |
+
}
|