{ "architectures": [ "BailingMMNativeForConditionalGeneration" ], "audio_tokenizer_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "AudioVAE" ], "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "dec_kwargs": { "backbone": { "_attn_implementation": "flash_attention_2", "attention_dropout": 0.0, "attn_implementation": null, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "is_causal": true, "max_position_embeddings": 32768, "max_window_layers": 0, "model_type": "qwen2", "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.43.1", "use_cache": false, "use_sliding_window": true, "vocab_size": 1 }, "latent_dim": 64, "output_dim": 320 }, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "enc_kwargs": { "backbone": { "_attn_implementation": "flash_attention_2", "attention_dropout": 0.0, "attn_implementation": null, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "is_causal": true, "max_position_embeddings": 32768, "max_window_layers": 0, "model_type": "qwen2", "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.43.1", "use_cache": false, "use_sliding_window": true, "vocab_size": 1 }, "hop_size": 320, "input_dim": 320, "latent_dim": 64 }, "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, "hifi_gan_disc_kwargs": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "init_method": "kaiming", "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "lambda_adv": 1.0, "lambda_disc": 1.0, "lambda_feat_match_loss": 1.0, "lambda_mel_loss": 15, "lambda_semantic": 5.0, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": -1, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "semantic_module_kwargs": { "casual": true, "whisper_encoder": { "n_ctx": 1500, "n_head": 20, "n_layer": 32, "n_mels": 128, "n_state": 1280 } }, "sep_token_id": null, "spec_disc_kwargs": 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, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false }, "auto_map": { "AutoConfig": "configuration_bailingmm.BailingMMConfig" }, "ditar_config": { "attn_backend": "torch", "attn_mask_enabled": false, "depth": 8, "dropout": 0.0, "hidden_size": 1024, "mlp_ratio": 4, "num_heads": 16, "pe_attn_head": null, "qk_norm": null }, "llm_config": { "_name_or_path": "", "add_cross_attention": false, "architectures": [ "BailingMoeForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_bailing_moe.BailingMoeConfig", "AutoModel": "modeling_bailing_moe.BailingMoeModel", "AutoModelForCausalLM": "modeling_bailing_moe.BailingMoeForCausalLM", "AutoModelForTokenClassification": "modeling_bailing_moe.BailingMoeForTokenClassification" }, "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, "early_stopping": false, "embedding_dropout": 0.0, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 126081, "exponential_decay_length_penalty": null, "finetuning_task": null, "first_k_dense_replace": 0, "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" }, "image_patch_token": 126346, "image_start_token": 126347, "initializer_range": 0.006, "intermediate_size": 5632, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 32768, "max_window_layers": 28, "min_length": 0, "model_type": "bailing_moe", "moe_intermediate_size": 1408, "multi_gate": true, "no_repeat_ngram_size": 0, "norm_head": false, "norm_softmax": false, "norm_topk_prob": true, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_experts": 64, "num_experts_per_tok": 6, "num_hidden_layers": 28, "num_key_value_heads": 4, "num_return_sequences": 1, "num_shared_experts": 2, "output_attentions": false, "output_dropout": 0.0, "output_hidden_states": false, "output_router_logits": false, "output_scores": false, "pad_token_id": 126081, "prefix": null, "pretraining_tp": 1, "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-05, "rope_scaling": { "factor": null, "type": "3D" }, "rope_theta": 600000, "sep_token_id": null, "sliding_window": 4096, "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, "typical_p": 1.0, "use_bfloat16": false, "use_bias": false, "use_cache": true, "use_qkv_bias": false, "use_sliding_window": false, "video_start_token": 126349, "vocab_size": 126464 }, "mlp_depth": 2, "model_type": "bailingmm", "torch_dtype": "bfloat16", "transformers_version": "4.52.4" }