Instructions to use karma689/mmbert-base-layer-detection-v1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use karma689/mmbert-base-layer-detection-v1.2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="karma689/mmbert-base-layer-detection-v1.2")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("karma689/mmbert-base-layer-detection-v1.2") model = AutoModelForTokenClassification.from_pretrained("karma689/mmbert-base-layer-detection-v1.2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ModernBertForTokenClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 2, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 1, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "dtype": "float32", | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 1, | |
| "global_attn_every_n_layers": 3, | |
| "gradient_checkpointing": false, | |
| "hidden_activation": "gelu", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "O", | |
| "1": "B-QUOTE", | |
| "2": "I-QUOTE", | |
| "3": "B-SABCHE", | |
| "4": "I-SABCHE", | |
| "5": "B-TSAWA", | |
| "6": "I-TSAWA", | |
| "7": "B-YIGCHUNG", | |
| "8": "I-YIGCHUNG", | |
| "9": "B-CHAPTER", | |
| "10": "I-CHAPTER", | |
| "11": "B-AUTHOR", | |
| "12": "I-AUTHOR", | |
| "13": "B-BOOKTITLE", | |
| "14": "I-BOOKTITLE" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "label2id": { | |
| "B-AUTHOR": 11, | |
| "B-BOOKTITLE": 13, | |
| "B-CHAPTER": 9, | |
| "B-QUOTE": 1, | |
| "B-SABCHE": 3, | |
| "B-TSAWA": 5, | |
| "B-YIGCHUNG": 7, | |
| "I-AUTHOR": 12, | |
| "I-BOOKTITLE": 14, | |
| "I-CHAPTER": 10, | |
| "I-QUOTE": 2, | |
| "I-SABCHE": 4, | |
| "I-TSAWA": 6, | |
| "I-YIGCHUNG": 8, | |
| "O": 0 | |
| }, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "local_attention": 128, | |
| "mask_token_id": 4, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "modernbert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 22, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "sans_pos", | |
| "rope_parameters": { | |
| "full_attention": { | |
| "rope_theta": 160000, | |
| "rope_type": "default" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 160000, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sep_token_id": 1, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.14.1", | |
| "use_cache": false, | |
| "vocab_size": 256000 | |
| } | |