config.json

{
  "architectures": [
    "OmniSpeech2SQwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "audio_generator_config": {
    "_attn_implementation_autoset": true,
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": [
      "Qwen3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bad_words_ids": null,
    "begin_suppress_tokens": null,
    "bos_token_id": 151643,
    "chunk_size_feed_forward": 0,
    "cross_attention_hidden_size": null,
    "decoder_start_token_id": null,
    "diversity_penalty": 0.0,
    "do_sample": false,
    "early_stopping": false,
    "encoder_no_repeat_ngram_size": 0,
    "eos_token_id": 151645,
    "exponential_decay_length_penalty": null,
    "finetuning_task": null,
    "forced_bos_token_id": null,
    "forced_eos_token_id": null,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 4096,
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "initializer_range": 0.02,
    "intermediate_size": 12288,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "llm_hidden_size": 4096,
    "max_length": 20,
    "max_position_embeddings": 40960,
    "max_seq_length": 8192,
    "max_window_layers": 28,
    "min_length": 0,
    "model_type": "qwen3",
    "mtp_num": 4,
    "no_repeat_ngram_size": 0,
    "num_attention_heads": 16,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 8,
    "num_key_value_heads": 8,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "return_dict": true,
    "return_dict_in_generate": false,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 1000000,
    "sep_token_id": null,
    "sliding_window": null,
    "speech_bos_token_id": 6561,
    "speech_eos_token_id": 6563,
    "speech_padding_token_id": 6564,
    "speech_sos_token_id": 6562,
    "speech_token_num": 5,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": false,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": "bfloat16",
    "torchscript": false,
    "txt_token_num": 1,
    "typical_p": 1.0,
    "use_bfloat16": false,
    "use_cache": true,
    "use_sliding_window": false,
    "vocab_size": 6565
  },
  "bos_token_id": 151643,
  "deepspeed_config": null,
  "eos_token_id": 151645,
  "gen_loss_weight": 1.0,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "max_position_embeddings": 40960,
  "max_window_layers": 36,
  "mm_tunable_parts": "backbone,speech_generator",
  "model_type": "omni_speech_qwen3",
  "num_attention_heads": 32,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "pretrain_tts": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "speech_encoder": "/nas_works/467836/checkpoints_sllms/whisper-large-v3",
  "speech_encoder_ds_rate": 5,
  "speech_encoder_hidden_size": 1280,
  "speech_encoder_type": "whisper",
  "speech_generator_config": "/nas_works/467836/VocalNet2/scripts/mtp/qwen3/vocalnet2_multistream_ar_config.json",
  "speech_generator_type": "multistream2_gate_arqwen3_mtp",
  "speech_projector_lr": null,
  "speech_projector_type": "linear",
  "tie_word_embeddings": false,
  "tokenizer_model_max_length": 4096,
  "tokenizer_padding_side": "right",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "tune_speech_generator_only": false,
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}