{ "_text_config_dict": { "_name_or_path": "Qwen/Qwen3-4B-Instruct-2507", "add_cross_attention": false, "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dtype": "bfloat16", "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2560, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 9728, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 262144, "max_window_layers": 36, "min_length": 0, "model_type": "qwen3", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 36, "num_key_value_heads": 8, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000, "sep_token_id": null, "sliding_window": null, "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": "4.57.3", "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "architectures": [ "SoriSpeechForConditionalGeneration" ], "audio_encoder_config": { "activation_function": "gelu", "attention_dropout": 0, "conv_chunksize": 500, "d_model": 1280, "downsample_hidden_size": 480, "dropout": 0, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layers": 32, "max_source_positions": 1500, "model_type": "sori_audio_encoder", "n_window": 50, "n_window_infer": 800, "num_mel_bins": 128, "output_dim": 2048, "scale_embedding": false }, "audio_end_token_id": 151671, "audio_start_token_id": 151670, "audio_to_llm_proj": true, "audio_token_id": 151669, "bos_token_id": 151643, "dtype": "float32", "eos_token_id": 151645, "llm_model_name_or_path": "Qwen/Qwen3-4B-Instruct-2507", "model_type": "sori_speech", "pad_token_id": 151643, "transformers_version": "4.57.3", "vocab_size": 151672, "text_config": { "vocab_size": 151672, "max_position_embeddings": 262144, "hidden_size": 2560, "intermediate_size": 9728, "num_hidden_layers": 36, "num_attention_heads": 32, "use_sliding_window": false, "sliding_window": null, "max_window_layers": 36, "num_key_value_heads": 8, "head_dim": 128, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "rope_theta": 5000000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "return_dict": true, "output_hidden_states": false, "torchscript": false, "dtype": "bfloat16", "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "architectures": [ "Qwen3ForCausalLM" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "task_specific_params": null, "problem_type": null, "tokenizer_class": null, "prefix": null, "bos_token_id": 151643, "pad_token_id": null, "eos_token_id": 151645, "sep_token_id": null, "decoder_start_token_id": null, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "num_beam_groups": 1, "diversity_penalty": 0.0, "_name_or_path": "Qwen/Qwen3-4B-Instruct-2507", "transformers_version": "4.57.3", "model_type": "qwen3", "tf_legacy_loss": false, "use_bfloat16": false, "output_attentions": false } }