{ "_name_or_path": "../models/emo-gliclass-audio-bi-1-wds-0.015-red-sum/checkpoint-1440", "architecture_type": "audio-bi-encoder", "architectures": [ "GLiClassModel" ], "audio_model_config": { "_attn_implementation_autoset": false, "_name_or_path": "facebook/wav2vec2-base-960h", "activation_dropout": 0.1, "adapter_attn_dim": null, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "add_cross_attention": false, "apply_spec_augment": true, "architectures": [ "Wav2Vec2ForCTC" ], "attention_dropout": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "codevector_dim": 256, "contrastive_logits_temperature": 0.1, "conv_bias": false, "conv_dim": [ 512, 512, 512, 512, 512, 512, 512 ], "conv_kernel": [ 10, 3, 3, 3, 3, 2, 2 ], "conv_stride": [ 5, 2, 2, 2, 2, 2, 2 ], "cross_attention_hidden_size": null, "ctc_loss_reduction": "sum", "ctc_zero_infinity": false, "decoder_start_token_id": null, "diversity_loss_weight": 0.1, "diversity_penalty": 0.0, "do_sample": false, "do_stable_layer_norm": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "feat_extract_activation": "gelu", "feat_extract_dropout": 0.0, "feat_extract_norm": "group", "feat_proj_dropout": 0.1, "feat_quantizer_dropout": 0.0, "final_dropout": 0.1, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.1, "length_penalty": 1.0, "mask_feature_length": 10, "mask_feature_min_masks": 0, "mask_feature_prob": 0.0, "mask_time_length": 10, "mask_time_min_masks": 2, "mask_time_prob": 0.05, "max_length": 20, "min_length": 0, "model_type": "wav2vec2", "no_repeat_ngram_size": 0, "num_adapter_layers": 3, "num_attention_heads": 12, "num_beam_groups": 1, "num_beams": 1, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 16, "num_conv_pos_embeddings": 128, "num_feat_extract_layers": 7, "num_hidden_layers": 12, "num_negatives": 100, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 768, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "problem_type": null, "proj_codevector_dim": 256, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "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, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_weighted_layer_sum": false, "vocab_size": 32, "xvector_output_dim": 512 }, "audio_model_name": "facebook/wav2vec2-base-960h", "audio_token_index": 50370, "class_token_index": 50368, "contrastive_loss_coef": 0.0, "embed_class_token": true, "encoder_config": { "_attn_implementation_autoset": false, "_name_or_path": "answerdotai/ModernBERT-base", "add_cross_attention": false, "architectures": [ "ModernBertForMaskedLM" ], "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 50281, "chunk_size_feed_forward": 0, "classifier_activation": "gelu", "classifier_bias": false, "classifier_dropout": 0.0, "classifier_pooling": "mean", "cls_token_id": 50281, "cross_attention_hidden_size": null, "decoder_bias": true, "decoder_start_token_id": null, "deterministic_flash_attn": false, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "embedding_dropout": 0.0, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 50282, "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", "1": "LABEL_1" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 1152, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "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": 22, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 50283, "position_embedding_type": "absolute", "prefix": null, "problem_type": null, "pruned_heads": {}, "reference_compile": null, "remove_invalid_values": false, "repad_logits_with_grad": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": 50282, "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, "torch_dtype": "float32", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "vocab_size": 50368 }, "encoder_model_name": "answerdotai/ModernBERT-base", "extract_text_features": false, "focal_loss_alpha": 0.9, "focal_loss_gamma": 2.5, "hidden_size": 768, "ignore_index": -100, "initializer_range": 0.03, "label_model_config": null, "label_model_name": null, "logit_scale_init_value": 2.6592, "max_num_classes": 25, "model_type": "GLiClass", "normalize_features": true, "pooling_strategy": "first", "projector_hidden_act": "gelu", "prompt_first": true, "scorer_type": "simple", "shuffle_labels": true, "squeeze_layers": false, "text_token_index": 50369, "torch_dtype": "float32", "transformers_version": "4.48.2", "use_lstm": false, "vocab_size": 50368 }