44 lines
1.2 KiB
JSON
44 lines
1.2 KiB
JSON
{
|
|
"architectures": [
|
|
"NewModel",
|
|
"NewForTokenClassification"
|
|
],
|
|
"attention_probs_dropout_prob": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration.NewConfig",
|
|
"AutoModelForMaskedLM": "modeling.NewForMaskedLM",
|
|
"AutoModel": "modeling.NewModel",
|
|
"AutoModelForMultipleChoice": "modeling.NewForMultipleChoice",
|
|
"AutoModelForQuestionAnswering": "modeling.NewForQuestionAnswering",
|
|
"AutoModelForSequenceClassification": "modeling.NewForSequenceClassification",
|
|
"AutoModelForTokenClassification": "modeling.NewForTokenClassification"
|
|
},
|
|
"classifier_dropout": 0.0,
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 768,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 3072,
|
|
"layer_norm_eps": 1e-12,
|
|
"layer_norm_type": "layer_norm",
|
|
"max_position_embeddings": 8192,
|
|
"model_type": "new",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 12,
|
|
"num_labels": 1,
|
|
"pack_qkv": true,
|
|
"pad_token_id": 1,
|
|
"position_embedding_type": "rope",
|
|
"rope_scaling": {
|
|
"factor": 8.0,
|
|
"type": "ntk"
|
|
},
|
|
"rope_theta": 20000,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.39.1",
|
|
"type_vocab_size": 1,
|
|
"unpad_inputs": false,
|
|
"use_memory_efficient_attention": false,
|
|
"vocab_size": 250048
|
|
}
|