config.json

{
  "architectures": [
    "SymphonyForConditionalGeneration"
  ],
  "encoder_config": {
    "compression_size": 50,
    "model_type": "symphony_speech_encoder",
    "n_ctx": 1500,
    "n_head": 20,
    "n_layer": 32,
    "n_mels": 128,
    "n_state": 1280,
    "stage_tokens": [
      80,
      80,
      80
    ]
  },
  "llm_config": {
    "_name_or_path": "Qwen/Qwen3-4B",
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": 151643,
    "eos_token_id": 151645,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9728,
    "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",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 40960,
    "max_window_layers": 36,
    "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": 1000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "torch_dtype": "bfloat16",
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 151936
  },
  "llm_modules": [
    "q_proj",
    "k_proj",
    "v_proj",
    "o_proj",
    "gate_proj",
    "up_proj",
    "down_proj"
  ],
  "lora_a": 64,
  "lora_r": 16,
  "low_resource": false,
  "model_type": "symphony",
  "auto_map": {
    "AutoConfig": "configuration_symphony.SymphonyConfig",
    "AutoModel": "modeling_symphony.SymphonyForConditionalGeneration",
    "AutoModelForCausalLM": "modeling_symphony.SymphonyForConditionalGeneration"
  },
  "torch_dtype": "float32",
  "transformers_version": "4.53.1"
}