| {"audio_config": {"hidden_size": 1280, "num_hidden_layers": 32, "intermediate_size": 5120, "num_attention_heads": 20, "num_key_value_heads": 20, "rms_norm_eps": 1e-05, "head_dim": 64, "rope_theta": 1000000.0, "vocab_size": 51866, "num_mel_bins": 128, "encoder_layers": 32, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "d_model": 1280, "dropout": 0.0, "attention_dropout": 0.0, "activation_function": "gelu", "activation_dropout": 0.0, "scale_embedding": false, "initializer_range": 0.02, "max_source_positions": 1500}, "text_config": {"model_type": "llama", "vocab_size": 131072, "max_position_embeddings": 131072, "hidden_size": 3072, "intermediate_size": 8192, "num_hidden_layers": 30, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "use_cache": true, "rope_theta": 100000000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "tie_word_embeddings": false, "bos_token_id": 1, "eos_token_id": 2, "sliding_window": null, "rope_traditional": false}, "model_repo": "mlx-community/Voxtral-Mini-3B-2507-bf16", "model_type": "voxtral", "audio_token_id": 24, "projector_hidden_act": "gelu", "vocab_size": 131072, "hidden_size": 3072, "quantization": {"group_size": 64, "bits": 4}, "quantization_config": {"group_size": 64, "bits": 4}} |