{ "_name_or_path": "sigridjineth/ko-reranker-v1-preview-240718", "architectures": [ "XLMRobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "auto_map": { "AutoConfig": "jinaai/jina-reranker-v2-base-multilingual--configuration_xlm_roberta.XLMRobertaFlashConfig", "AutoModel": "jinaai/jina-reranker-v2-base-multilingual--modeling_xlm_roberta.XLMRobertaModel", "AutoModelForSequenceClassification": "jinaai/jina-reranker-v2-base-multilingual--modeling_xlm_roberta.XLMRobertaForSequenceClassification" }, "bos_token_id": 0, "classifier_dropout": null, "emb_pooler": null, "eos_token_id": 2, "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-05, "load_trained_adapters": false, "lora_adaptations": null, "lora_alpha": 1, "lora_dropout_p": 0.0, "lora_main_params_trainable": false, "lora_rank": 4, "matryoshka_dimensions": null, "max_position_embeddings": 1026, "num_attention_heads": 12, "num_hidden_layers": 12, "output_past": true, "pad_token_id": 1, "position_embedding_type": "absolute", "torch_dtype": "bfloat16", "transformers_version": "4.42.4", "truncate_dim": null, "type_vocab_size": 1, "use_cache": false, "use_flash_attn": true, "vocab_size": 250002 }