{ "architectures": [ "Bailing_qwen2_5NativeForConditionalGeneration" ], "audio_config": null, "llm_config": { "_attn_implementation_autoset": false, "_name_or_path": null, "add_cross_attention": false, "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "audio_end_token": 151695, "audio_id_shift": 151701, "audio_patch_token": 151693, "audio_start_token": 151694, "audio_vocab_size": 4099, "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, "encoder_no_repeat_ngram_size": 0, "end_of_audio_token": 151692, "end_of_chunk_token": 151691, "eos_token_id": 151645, "exponential_decay_length_penalty": null, "finetuning_task": null, "first_signal_token": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "frame_patch_token": 151700, "gen_audio_end_token": 151698, "gen_audio_patch_token": 151696, "gen_audio_start_token": 151697, "gen_image_end_token": 151689, "gen_image_patch_token": 151687, "gen_image_start_token": 151688, "hidden_act": "silu", "hidden_size": 3584, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_end_token": 151684, "image_patch_token": 151682, "image_start_token": 151683, "image_token_id": 151682, "initializer_range": 0.02, "intermediate_size": 18944, "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": "qwen2", "no_repeat_ngram_size": 0, "num_attention_heads": 28, "num_audio_token": 256, "num_beam_groups": 1, "num_beams": 1, "num_decoder_audio_token": 512, "num_decoder_image_token": 1024, "num_hidden_layers": 28, "num_image_token": 1280, "num_key_value_heads": 4, "num_return_sequences": 1, "num_video_token": 5120, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "placeholder_audio_token_in_text": 151699, "placeholder_image_token_in_text": 151690, "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": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sep_token_id": null, "sliding_window": 131072, "spatial_merge_size": 2, "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, "tokens_per_second": 2, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "use_llm_3drope": "m_rope", "use_sliding_window": false, "video_end_token": 151686, "video_patch_token": 151682, "video_start_token": 151685, "vocab_size": 152064 }, "llm_type": "qwen2_5", "mlp_depths": 2, "model_type": "bailing_qwen2_5", "num_decoder_audio_token": 512, "num_decoder_image_token": 1024, "num_query_token_audio": 256, "num_query_token_image": 64, "num_query_token_video": 64, "select_layer": -1, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_llm_lora": 0, "use_vit_lora": 0, "vision_config": { "_attn_implementation_autoset": true, "_name_or_path": null, "add_cross_attention": false, "architectures": [ "Qwen2_5_VisionTransformer" ], "auto_map": { "AutoConfig": "configuration_qwen2_5_vit.Qwen2_5_VLVisionConfig", "AutoModel": "qwen2_5_vit.Qwen2_5_VisionTransformer" }, "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, "depth": 32, "diversity_penalty": 0.0, "do_sample": false, "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, "fullatt_block_indexes": [ 7, 15, 23, 31 ], "hidden_act": "silu", "hidden_size": 1280, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "in_channels": 3, "in_chans": 3, "intermediate_size": 3456, "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": "qwen2_5_vit", "no_repeat_ngram_size": 0, "num_beam_groups": 1, "num_beams": 1, "num_heads": 16, "num_return_sequences": 1, "out_hidden_size": 8192, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "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": 14, "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, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "window_size": 112 }, "vision_type": "qwen2_5_vit" }