mlynatom's picture
push
3c46f6c verified
{
"_name_or_path": "chandar-lab/NeoBERT",
"architectures": [
"NeoBERTForSequenceClassification"
],
"auto_map": {
"AutoConfig": "chandar-lab/NeoBERT--model.NeoBERTConfig",
"AutoModel": "chandar-lab/NeoBERT--model.NeoBERT",
"AutoModelForMaskedLM": "chandar-lab/NeoBERT--model.NeoBERTLMHead",
"AutoModelForSequenceClassification": "chandar-lab/NeoBERT--model.NeoBERTForSequenceClassification"
},
"classifier_init_range": 0.02,
"decoder_init_range": 0.02,
"dim_head": 64,
"embedding_init_range": 0.02,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4"
},
"intermediate_size": 3072,
"kwargs": {
"_commit_hash": "a4fbc49a61db10ff2db66140ae59c09d96c027f9",
"architectures": [
"NeoBERTLMHead"
],
"attn_implementation": null,
"auto_map": {
"AutoConfig": "chandar-lab/NeoBERT--model.NeoBERTConfig",
"AutoModel": "chandar-lab/NeoBERT--model.NeoBERT",
"AutoModelForMaskedLM": "chandar-lab/NeoBERT--model.NeoBERTLMHead",
"AutoModelForSequenceClassification": "chandar-lab/NeoBERT--model.NeoBERTForSequenceClassification"
},
"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": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4
},
"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",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.47.0",
"trust_remote_code": true,
"vocab_size": 30522
}