49 lines
1.7 KiB
JSON
49 lines
1.7 KiB
JSON
{
|
|
"_name_or_path": "intfloat/multilingual-e5-base",
|
|
"adaptive": true,
|
|
"architectures": [
|
|
"LSGXLMRobertaModel"
|
|
],
|
|
"attention_probs_dropout_prob": 0.1,
|
|
"auto_map": {
|
|
"AutoConfig": "modeling_lsg_xlm_roberta.LSGXLMRobertaConfig",
|
|
"AutoModel": "modeling_lsg_xlm_roberta.LSGXLMRobertaModel",
|
|
"AutoModelForCausalLM": "modeling_lsg_xlm_roberta.LSGXLMRobertaForCausalLM",
|
|
"AutoModelForMaskedLM": "modeling_lsg_xlm_roberta.LSGXLMRobertaForMaskedLM",
|
|
"AutoModelForMultipleChoice": "modeling_lsg_xlm_roberta.LSGXLMRobertaForMultipleChoice",
|
|
"AutoModelForQuestionAnswering": "modeling_lsg_xlm_roberta.LSGXLMRobertaForQuestionAnswering",
|
|
"AutoModelForSequenceClassification": "modeling_lsg_xlm_roberta.LSGXLMRobertaForSequenceClassification",
|
|
"AutoModelForTokenClassification": "modeling_lsg_xlm_roberta.LSGXLMRobertaForTokenClassification"
|
|
},
|
|
"base_model_prefix": "lsg",
|
|
"block_size": 128,
|
|
"bos_token_id": 0,
|
|
"classifier_dropout": null,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 768,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 3072,
|
|
"layer_norm_eps": 1e-05,
|
|
"lsh_num_pre_rounds": 1,
|
|
"mask_first_token": false,
|
|
"max_position_embeddings": 4098,
|
|
"model_type": "xlm-roberta",
|
|
"num_attention_heads": 12,
|
|
"num_global_tokens": 1,
|
|
"num_hidden_layers": 12,
|
|
"output_past": true,
|
|
"pad_token_id": 1,
|
|
"pool_with_global": true,
|
|
"position_embedding_type": "absolute",
|
|
"sparse_block_size": 128,
|
|
"sparsity_factor": 2,
|
|
"sparsity_type": "norm",
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.30.2",
|
|
"type_vocab_size": 1,
|
|
"use_cache": true,
|
|
"vocab_size": 250002
|
|
}
|