Instructions to use htet-98/mmbert_base_oversampling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use htet-98/mmbert_base_oversampling with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="htet-98/mmbert_base_oversampling")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("htet-98/mmbert_base_oversampling") model = AutoModelForSequenceClassification.from_pretrained("htet-98/mmbert_base_oversampling") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ModernBertForSequenceClassification" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_probs_dropout_prob": 0.1, | |
| "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_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "affiliation", | |
| "1": "aggression", | |
| "2": "self-deprecate", | |
| "3": "self-enhance" | |
| }, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "label2id": { | |
| "affiliation": 0, | |
| "aggression": 1, | |
| "self-deprecate": 2, | |
| "self-enhance": 3 | |
| }, | |
| "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", | |
| "problem_type": "single_label_classification", | |
| "repad_logits_with_grad": false, | |
| "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": "5.0.0", | |
| "use_cache": false, | |
| "vocab_size": 256000 | |
| } | |