{ "adding_text_hiddenstates": false, "architectures": [ "LycheeFullDuplex" ], "audio_encoder_config": { "adapter_stride": 2, "kernel_size": 3, "llm_dim": 3584, "model_type": "step_audio_2_encoder", "n_audio_ctx": 1500, "n_audio_head": 20, "n_audio_layer": 32, "n_audio_state": 1280, "n_codebook_size": 4096, "n_mels": 128 }, "audio_pad_token_id": 158360, "auto_map": { "AutoConfig": "configuration_step_audio_2.StepAudio2Config", "AutoModelForCausalLM": "modeling_step_audio_2.StepAudio2ForCausalLM" }, "control_branch_layer": 8, "control_layer_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 3584, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 18944, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention" ], "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 16384, "max_window_layers": 28, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_groups": 4, "num_attention_heads": 28, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 4, "num_key_value_heads": 4, "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": 1000000.0, "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": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_sliding_window": false, "vocab_size": 158363 }, "control_token_chunk_size": 10, "control_token_focal_loss_beta": 2.0, "control_token_ids_max": 158356, "control_token_ids_min": 158352, "control_token_use_focal_loss": false, "detect_token_id": 158356, "end_bc_token_id": 158353, "keep_bc_token_id": 158362, "keep_listening_token_id": 158354, "keep_speaking_token_id": 158355, "max_window_layers": null, "merge_layer_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 3584, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 18944, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention" ], "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 16384, "max_window_layers": 28, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_groups": 4, "num_attention_heads": 28, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 4, "num_key_value_heads": 4, "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": 1000000.0, "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": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_sliding_window": false, "vocab_size": 158363 }, "model_type": "step_audio_2_full_duplex", "no_stoken_label": false, "no_text_label": false, "sleep_token_id": 158357, "sliding_window": 2048, "start_bc_token_id": 158362, "start_listening_token_id": 158353, "start_speaking_token_id": 158352, "stoken_delay_num": 10, "stoken_delay_token_id": 158361, "stoken_layer_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 3584, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 18944, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention" ], "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 16384, "max_window_layers": 28, "min_length": 0, "model_type": "qwen2", "no_repeat_ngram_size": 0, "num_attention_groups": 4, "num_attention_heads": 28, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 4, "num_key_value_heads": 4, "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": 1000000.0, "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": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_sliding_window": false, "vocab_size": 158363 }, "stoken_pad_token_id": 158359, "stoken_token_ids_max": 158352, "stoken_token_ids_min": 151694, "text_config": { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "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" ], "max_position_embeddings": 16384, "max_window_layers": 28, "model_type": "qwen2", "num_attention_groups": 4, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 158363 }, "text_pad_token_id": 158358, "text_sleep_token_id": null, "torch_dtype": "bfloat16", "transformers_version": "4.53.1", "use_sliding_window": false }