{ "_name_or_path": "/home/stefan/Repositories/NeoBERT", "architectures": [ "NeoBERTForTokenClassification" ], "auto_map": { "AutoConfig": "model.NeoBERTConfig", "AutoModel": "model.NeoBERT", "AutoModelForMaskedLM": "model.NeoBERTLMHead", "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification", "AutoModelForTokenClassification": "model.NeoBERTForTokenClassification" }, "classifier_init_range": 0.02, "decoder_init_range": 0.02, "dim_head": 64, "embedding_init_range": 0.02, "finetuning_task": "ner", "hidden_size": 768, "id2label": { "0": "O", "1": "B-PER", "2": "I-PER", "3": "B-ORG", "4": "I-ORG", "5": "B-LOC", "6": "I-LOC", "7": "B-MISC", "8": "I-MISC" }, "intermediate_size": 3072, "kwargs": { "_commit_hash": null, "architectures": [ "NeoBERTLMHead" ], "attn_implementation": null, "auto_map": { "AutoConfig": "model.NeoBERTConfig", "AutoModel": "model.NeoBERT", "AutoModelForMaskedLM": "model.NeoBERTLMHead", "AutoModelForSequenceClassification": "model.NeoBERTForSequenceClassification", "AutoModelForTokenClassification": "model.NeoBERTForTokenClassification" }, "classifier_init_range": 0.02, "dim_head": 64, "kwargs": { "classifier_init_range": 0.02, "pretrained_model_name_or_path": "google-bert/bert-base-uncased", "trust_remote_code": true }, "model_type": "neobert", "pretrained_model_name_or_path": "google-bert/bert-base-uncased", "torch_dtype": "float32", "transformers_version": "4.48.2", "trust_remote_code": true }, "label2id": { "B-LOC": 5, "B-MISC": 7, "B-ORG": 3, "B-PER": 1, "I-LOC": 6, "I-MISC": 8, "I-ORG": 4, "I-PER": 2, "O": 0 }, "max_length": 4096, "model_type": "neobert", "norm_eps": 1e-05, "num_attention_heads": 12, "num_hidden_layers": 28, "pad_token_id": 0, "pretrained_model_name_or_path": "google-bert/bert-base-uncased", "torch_dtype": "float32", "transformers_version": "4.49.0", "trust_remote_code": true, "vocab_size": 30522 }