{ "architectures": [ "MultiEnc_Qwen3VLForConditionalGeneration" ], "dtype": "bfloat16", "eos_token_id": 151645, "hidden_size": 4096, "image_token_id": 151655, "model_type": "qwen3_vl", "pad_token_id": 151643, "text_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "float32", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 262144, "model_type": "qwen3_vl_text", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_interleaved": true, "mrope_section": [ 24, 20, 20 ], "rope_type": "default" }, "rope_theta": 5000000, "use_cache": false, "vocab_size": 151936 }, "tie_word_embeddings": false, "transformers_version": "4.57.0", "use_cache": false, "video_token_id": 151656, "vision_config": { "fusion_type": "cross_attn_local3x3_expansion5_cascade1_drop-enc-0.1", "llm_hidden_size": 4096, "model_type": "multi_enc_vision_wrapper", "spatial_merge_size": 2, "tokens_per_second": null, "vision_model_config": { "convnext": { "model_cfg": { "embed_dim": 768, "hidden_sizes": [ 192, 384, 768, 1536 ], "text_cfg": { "context_length": 77, "heads": 12, "layers": 16, "vocab_size": 49408, "width": 768 }, "vision_cfg": { "image_size": 320, "timm_drop": 0.0, "timm_drop_path": 0.1, "timm_model_name": "convnext_large", "timm_model_pretrained": false, "timm_pool": "", "timm_proj": "mlp" } }, "preprocess_cfg": { "mean": [ 0.48145466, 0.4578275, 0.40821073 ], "std": [ 0.26862954, 0.26130258, 0.27577711 ] } }, "dinov2": { "_name_or_path": "ckpts/models/dinov2-large", "add_cross_attention": false, "apply_layernorm": true, "architectures": [ "Dinov2Model" ], "attention_probs_dropout_prob": 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_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "drop_path_rate": 0.0, "dtype": "float32", "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", "hidden_dropout_prob": 0.0, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "image_size": 518, "initializer_range": 0.02, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-06, "layerscale_value": 1.0, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "mlp_ratio": 4, "model_type": "dinov2", "no_repeat_ngram_size": 0, "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "out_features": [ "stage24" ], "out_indices": [ 24 ], "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "reshape_hidden_states": true, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "stage_names": [ "stem", "stage1", "stage2", "stage3", "stage4", "stage5", "stage6", "stage7", "stage8", "stage9", "stage10", "stage11", "stage12", "stage13", "stage14", "stage15", "stage16", "stage17", "stage18", "stage19", "stage20", "stage21", "stage22", "stage23", "stage24" ], "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, "transformers_version": "4.57.0", "typical_p": 1.0, "use_bfloat16": false, "use_mask_token": true, "use_swiglu_ffn": false }, "original_enc": { "_name_or_path": "", "add_cross_attention": false, "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": "float32", "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" }, "in_channels": 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_vl", "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": 4096, "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, "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, "top_k": 50, "top_p": 1.0, "torchscript": false, "transformers_version": "4.57.0", "typical_p": 1.0, "use_bfloat16": false }, "pe_3d": { "attn_pooler_heads": 8, "depth_patch_size": 8, "drop_path": 0.2, "heads": 16, "image_size": 128, "layers": 24, "ls_init_value": null, "mlp_ratio": 4.0, "output_dim": null, "patch_size": 8, "pool_type": "none", "use_abs_posemb": true, "use_cls_token": false, "use_ln_post": true, "use_ln_pre": true, "use_rope": true, "width": 1024 } } }, "vision_end_token_id": 151653, "vision_start_token_id": 151652 }