{ "architectures": [ "OpenProvenceForSequenceClassification" ], "auto_map": { "AutoConfig": "modeling_open_provence_standalone.OpenProvenceConfig", "AutoModel": "modeling_open_provence_standalone.OpenProvenceForSequenceClassification", "AutoModelForSequenceClassification": "modeling_open_provence_standalone.OpenProvenceForSequenceClassification", "AutoModelForTokenClassification": "modeling_open_provence_standalone.OpenProvenceForTokenClassification" }, "base_model_config": { "_name_or_path": "cl-nagoya/ruri-v3-reranker-310m", "add_cross_attention": false, "architectures": [ "ModernBertForSequenceClassification" ], "attention_bias": false, "attention_dropout": 0.0, "attn_implementation": "eager", "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_activation": "gelu", "classifier_bias": false, "classifier_dropout": 0.0, "classifier_pooling": "cls", "cls_token_id": 6, "cross_attention_hidden_size": null, "decoder_bias": true, "decoder_start_token_id": null, "deterministic_flash_attn": false, "diversity_penalty": 0.0, "do_sample": false, "dtype": "float32", "early_stopping": false, "embedding_dropout": 0.0, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "global_attn_every_n_layers": 3, "global_rope_theta": 160000.0, "gradient_checkpointing": false, "hidden_activation": "gelu", "hidden_size": 768, "id2label": { "0": "LABEL_0" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-05, "length_penalty": 1.0, "local_attention": 128, "local_rope_theta": 10000.0, "max_length": 20, "max_position_embeddings": 8192, "min_length": 0, "mlp_bias": false, "mlp_dropout": 0.0, "model_type": "modernbert", "no_repeat_ngram_size": 0, "norm_bias": false, "norm_eps": 1e-05, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 25, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 3, "position_embedding_type": "rope", "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repad_logits_with_grad": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": 4, "sparse_pred_ignore_index": -100, "sparse_prediction": false, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torchscript": false, "transformers_version": "4.57.5", "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 102400 }, "base_model_name_or_path": "hotchpotch/open-provence-reranker-large-v1", "default_threadshold": null, "default_threshold": null, "encoder_architecture": "modernbert", "hidden_size": 768, "id2label": { "0": "LABEL_0" }, "label2id": { "LABEL_0": 0 }, "max_length": 4096, "mode": "reranking_pruning", "model_type": "open_provence", "num_pruning_labels": 2, "pruning_config": { "classifier_dropout": 0.0, "hidden_size": 768, "num_labels": 2, "sentence_pooling": "mean", "use_weighted_pooling": false }, "tokenizer_name_or_path": null, "transformers_version": "4.57.5", "vocab_size": 102400 }