| { | |
| "_name_or_path": "/content/labse_lsg_model", | |
| "adaptive": true, | |
| "architectures": [ | |
| "BertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "modeling_lsg_bert.LSGBertConfig", | |
| "AutoModel": "modeling_lsg_bert.LSGBertModel", | |
| "AutoModelForCausalLM": "modeling_lsg_bert.LSGBertLMHeadModel", | |
| "AutoModelForMaskedLM": "modeling_lsg_bert.LSGBertForMaskedLM", | |
| "AutoModelForMultipleChoice": "modeling_lsg_bert.LSGBertForMultipleChoice", | |
| "AutoModelForPreTraining": "modeling_lsg_bert.LSGBertForPreTraining", | |
| "AutoModelForQuestionAnswering": "modeling_lsg_bert.LSGBertForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modeling_lsg_bert.LSGBertForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_lsg_bert.LSGBertForTokenClassification" | |
| }, | |
| "base_model_prefix": "lsg", | |
| "block_size": 128, | |
| "classifier_dropout": null, | |
| "directionality": "bidi", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "lsh_num_pre_rounds": 1, | |
| "mask_first_token": false, | |
| "max_position_embeddings": 4096, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_global_tokens": 7, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pool_with_global": true, | |
| "pooler_fc_size": 768, | |
| "pooler_num_attention_heads": 12, | |
| "pooler_num_fc_layers": 3, | |
| "pooler_size_per_head": 128, | |
| "pooler_type": "first_token_transform", | |
| "position_embedding_type": "absolute", | |
| "sparse_block_size": 128, | |
| "sparsity_factor": 2, | |
| "sparsity_type": "norm", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.40.2", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 501153 | |
| } | |