{ "architectures": [ "FunAudioChatForConditionalGeneration" ], "audio_config": { "activation_dropout": 0, "activation_function": "gelu", "attention_dropout": 0, "bos_token_id": 6561, "codebook_size": 6565, "continuous_features_mode": "replace", "crq_transformer_config": { "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3072, "max_position_embeddings": 32768, "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, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.51.0", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "d_model": 1280, "dropout": 0, "enable_audio_invert_tower": true, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layers": 32, "eos_token_id": 6562, "group_size": 5, "initializer_range": 0.02, "max_source_positions": 1500, "model_type": "funaudiochat_audio_encoder", "n_window": 100, "num_hidden_layers": 32, "num_mel_bins": 128, "output_dim": 4096, "pad_token_id": 6563, "scale_embedding": false, "torch_dtype": "bfloat16" }, "audio_token_index": 151669, "ignore_index": -100, "model_type": "funaudiochat", "text_config": { "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "audio_bos_index": 151670, "audio_eos_index": 151671, "bos_token_id": 151643, "eos_token_id": 151643, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 262144, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 5000000, "sil_index": 151673, "sliding_window": null, "torch_dtype": "bfloat16", "use_cache": false, "use_sliding_window": false, "vocab_size": 151936 }, "torch_dtype": "bfloat16", "transformers_version": "4.52.3", "use_cache": false }