|
{ |
|
"_name_or_path": "BAAI/bge-base-en-v1.5", |
|
"architectures": [ |
|
"BertModel" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"gradient_checkpointing": false, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "LABEL_0" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"LABEL_0": 0 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"neuron": { |
|
"auto_cast": null, |
|
"auto_cast_type": null, |
|
"compiler_type": "neuronx-cc", |
|
"compiler_version": "2.11.0.34+c5231f848", |
|
"disable_fallback": false, |
|
"disable_fast_relayout": false, |
|
"dynamic_batch_size": false, |
|
"input_names": [ |
|
"input_ids", |
|
"attention_mask", |
|
"token_type_ids" |
|
], |
|
"output_names": [ |
|
"last_hidden_state", |
|
"pooler_output" |
|
], |
|
"static_batch_size": 1, |
|
"static_sequence_length": 384 |
|
}, |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 0, |
|
"position_embedding_type": "absolute", |
|
"task": null, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.35.0", |
|
"type_vocab_size": 2, |
|
"use_cache": true, |
|
"vocab_size": 30522 |
|
} |
|
|