{ "architectures": [ "VoilaModel" ], "attention_bias": false, "attention_dropout": 0.0, "audio_chat_ref_end_token_id": 136455, "audio_chat_ref_start_token_id": 136454, "audio_chat_ref_token_id": 136456, "audio_ref_token_pos": 4, "audio_token_id": 136457, "audio_tts_ref_end_token_id": 136452, "audio_tts_ref_start_token_id": 136451, "audio_tts_ref_token_id": 136453, "bos_token_id": 128000, "codebook_size": 2048, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_audio_token_id": 136447, "max_position_embeddings": 8192, "min_audio_token_id": 128256, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_codebooks": 4, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "vocab_size": 136512 }