| { | |
| "architectures": [ | |
| "Qwen3OmniMoeForConditionalGeneration" | |
| ], | |
| "assistant_token_id": 77091, | |
| "code2wav_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "codebook_dim": 512, | |
| "codebook_size": 2048, | |
| "decoder_dim": 1536, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "intermediate_size": 3072, | |
| "layer_scale_initial_scale": 0.01, | |
| "max_position_embeddings": 8000, | |
| "model_type": "", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 16, | |
| "num_quantizers": 16, | |
| "num_semantic_quantizers": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000, | |
| "semantic_codebook_size": 4096, | |
| "sliding_window": 72, | |
| "upsample_rates": [ | |
| 8, | |
| 5, | |
| 4, | |
| 3 | |
| ], | |
| "upsampling_ratios": [ | |
| 2, | |
| 2 | |
| ], | |
| "vector_quantization_hidden_dimension": 512 | |
| }, | |
| "dtype": "bfloat16", | |
| "enable_audio_output": true, | |
| "im_end_token_id": 151645, | |
| "im_start_token_id": 151644, | |
| "model_type": "qwen3_omni_moe", | |
| "system_token_id": 8948, | |
| "talker_config": { | |
| "accept_hidden_layer": 24, | |
| "audio_end_token_id": 151670, | |
| "audio_start_token_id": 151669, | |
| "audio_token_id": 151675, | |
| "code_predictor_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0, | |
| "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, | |
| "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": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "min_length": 0, | |
| "model_type": "qwen3_omni_moe_talker_code_predictor", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_code_groups": 16, | |
| "num_hidden_layers": 5, | |
| "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, | |
| "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_sliding_window": false, | |
| "vocab_size": 2048 | |
| }, | |
| "codec_bos_id": 2149, | |
| "codec_eos_token_id": 2150, | |
| "codec_nothink_id": 2155, | |
| "codec_pad_id": 2148, | |
| "codec_think_bos_id": 2156, | |
| "codec_think_eos_id": 2157, | |
| "image_token_id": 151655, | |
| "model_type": "", | |
| "num_code_groups": 16, | |
| "output_router_logits": false, | |
| "position_id_per_seconds": 13, | |
| "seconds_per_chunk": 2, | |
| "spatial_merge_size": 2, | |
| "speaker_id": { | |
| "aiden": 2303, | |
| "chelsie": 2301, | |
| "ethan": 2302 | |
| }, | |
| "text_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 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": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "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_talker_text", | |
| "moe_intermediate_size": 384, | |
| "no_repeat_ngram_size": 0, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 6, | |
| "num_hidden_layers": 20, | |
| "num_key_value_heads": 2, | |
| "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_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": 768, | |
| "sliding_window": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "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_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 3072 | |
| }, | |
| "thinker_hidden_size": 2048, | |
| "video_token_id": 151656, | |
| "vision_start_token_id": 151652 | |
| }, | |
| "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_index": 151675, | |
| "dtype": "bfloat16", | |
| "image_token_index": 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": 1024, | |
| "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": 256, | |
| "no_repeat_ngram_size": 0, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 16, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_experts": 8, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 4, | |
| "num_key_value_heads": 2, | |
| "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_index": 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_position_embeddings": 2304, | |
| "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 | |
| } | |