{ "model_type": "moss_tts_delay", "architectures": [ "MossTTSDelayModel" ], "auto_map": { "AutoConfig": "configuration_moss_tts.MossTTSDelayConfig", "AutoModel": "modeling_moss_tts.MossTTSDelayModel" }, "dtype": "bfloat16", "initializer_range": 0.02, "language_config": { "_name_or_path": "Qwen/Qwen3-8B", "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "pad_token_id": 151643, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "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": 40960, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "use_cache": true, "use_sliding_window": false, "vocab_size": 155648 }, "n_vq": 32, "audio_vocab_size": 1024, "audio_user_slot_token_id": 151654, "audio_assistant_gen_slot_token_id": 151656, "audio_assistant_delay_slot_token_id": 151662, "audio_start_token_id": 151652, "audio_end_token_id": 151653, "audio_pad_code": 1024, "sampling_rate": 24000, "transformers_version": "4.57.1", "additional_mlp_ffn_hidden_size": 2048, "local_ffn_hidden_size": 8960, "local_hidden_size": 1536, "local_num_layers": 4 }