{ "architectures": [ "Qwen3OmniMoeForConditionalGeneration" ], "assistant_token_id": 77091, "dtype": "bfloat16", "enable_audio_output": false, "im_end_token_id": 151645, "im_start_token_id": 151644, "model_type": "qwen3_omni_moe", "system_token_id": 8948, "thinker_config": { "audio_config": { "_name_or_path": "", "activation_dropout": 0, "activation_function": "gelu", "add_cross_attention": false, "architectures": null, "attention_dropout": 0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "conv_chunksize": 500, "cross_attention_hidden_size": null, "d_model": 1280, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "downsample_hidden_size":480, "dropout": 0, "dtype": null, "early_stopping": false, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layers": 32, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_source_positions": 1500, "min_length": 0, "model_type": "qwen3_omni_moe_audio_encoder", "n_window": 50, "n_window_infer": 800, "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 32, "num_mel_bins": 128, "num_return_sequences": 1, "output_attentions": false, "output_dim": 2048, "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, "scale_embedding": false, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false }, "audio_end_token_id": 151670, "audio_start_token_id": 151669, "audio_token_id": 151675, "dtype": "bfloat16", "image_token_id": 151655, "initializer_range": 0.02, "model_type": "qwen3_omni_moe_thinker", "position_id_per_seconds": 13, "seconds_per_chunk": 2, "text_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": null, "attention_bias": false, "attention_dropout": 0.0, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_sparse_step": 1, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "dtype": null, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "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": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 768, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 65536, "min_length": 0, "mlp_only_layers": [], "model_type": "qwen3_omni_moe_text", "moe_intermediate_size": 768, "no_repeat_ngram_size": 0, "norm_topk_prob": true, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_experts": 128, "num_experts_per_tok": 8, "num_hidden_layers": 48, "num_key_value_heads": 4, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_router_logits": 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": { "interleaved": true, "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000, "router_aux_loss_coef": 0.001, "sep_token_id": null, "shared_expert_intermediate_size": 0, "sliding_window": null, "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, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_qk_norm": true, "use_sliding_window": false, "vocab_size": 152064 }, "user_token_id": 872, "video_token_id": 151656, "vision_config": { "_name_or_path": "", "add_cross_attention": false, "apply_vit_abs_pos_embed": true, "architectures": null, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "deepstack_visual_indexes": [ 8, 16, 24 ], "depth": 27, "diversity_penalty": 0.0, "do_sample": false, "dtype": null, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 768, "in_channels": 3, "in_chans": 3, "initializer_range": 0.02, "intermediate_size": 4304, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "qwen3_omni_moe_vision_encoder", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_heads": 16, "num_return_sequences": 1, "out_hidden_size": 2048, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 16, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "spatial_merge_size": 2, "spatial_patch_size": 16, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "temporal_patch_size": 2, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "tokens_per_second": 2, "top_k": 50, "top_p": 1.0, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false }, "vision_end_token_id": 151653, "vision_start_token_id": 151652 }, "transformers_version": "4.57.0.dev0", "tts_bos_token_id": 151672, "tts_eos_token_id": 151673, "tts_pad_token_id": 151671, "user_token_id": 872 }