{ "add_classification_head": false, "anyres_pooling_size": 2, "anyres_vit_max_image_size": 2048, "anyres_vit_two_views": false, "architectures": [ "HunYuanVLV1ForConditionalGeneration" ], "attention_bias": false, "attention_dropout": 0.0, "attention_head_dim": 128, "bos_token_id": 120000, "cla_share_factor": 2, "class_num": 0, "dense_list": [ 1024, 0 ], "eod_token_id": 120020, "eos_token_id": 120020, "group_limited_greedy": false, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "im_end_id": 120119, "im_newline_id": 120121, "im_start_id": 120118, "image_token_id": 120120, "initializer_range": 0.02, "intermediate_size": 3584, "kv_lora_rank": null, "mask_init_id": 13, "max_position_embeddings": 32768, "tie_word_embeddings": true, "mlp_bias": false, "model_type": "hunyuan_v1_vl", "moe_drop_tokens": false, "moe_intermediate_size": null, "moe_layer_num_skipped": 0, "moe_random_routing_dropped_token": false, "moe_topk": null, "mtp_loss_factor": 0.3, "mtp_moe_layer_num_skipped": 0, "mtp_no_bias": false, "mtp_type": "moe", "n_group": null, "norm_topk_prob": true, "norm_type": "rms", "num_attention_heads": 16, "num_experts": 1, "num_hidden_layers": 24, "num_key_value_heads": 8, "num_media_embeds": 257, "num_nextn_predict_layers": 1, "num_predictor_layers": 1, "num_shared_expert": null, "org_vocab_size": 120818, "pad_id": 120002, "pad_token_id": 120002, "pool_type": "last", "position_embedding_xdrope": false, "pretraining_tp": 1, "q_lora_rank": null, "qk_nope_head_dim": null, "qk_rope_head_dim": null, "rms_norm_eps": 1e-05, "rope_scaling": { "alpha": 1000.0, "beta_fast": 32, "beta_slow": 1, "factor": 1.0, "mscale": 1.0, "mscale_all_dim": 1.0, "type": "dynamic" }, "rope_theta": 10000.0, "routed_scaling_factor": 1.0, "sep_token_id": 0, "skip_cls_token": true, "text_end_id": 8, "text_start_id": 7, "tie_word_embeddings": true, "topk_group": null, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "use_cla": false, "use_mixed_mlp_moe": false, "use_mla": false, "use_qk_norm": true, "use_rotary_pos_emb": true, "v_head_dim": null, "video_end_id": 120123, "video_start_id": 120122, "vision_config": { "adaptor_patch_size": 2, "add_patchemb_bias": true, "attention_dropout": 0.0, "cat_extra_token": 1, "fuse_vit_feature": 0, "hidden_act": "gelu", "hidden_dropout": 0.0, "hidden_size": 1152, "img_max_token_num": 4096, "intermediate_size": 4304, "interpolate_mode": "bilinear", "layer_norm_eps": 1e-05, "max_image_size": 2048, "max_vit_seq_len": 16384, "num_key_value_heads": 16, "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "out_hidden_size": 1024, "patch_size": 16, "use_qk_norm": true, "attention_bias": false, "rms_norm_eps": 1e-05, "xdrope_section": [ 0.25, 0.25, 0.25, 0.25 ], "use_rotary_pos_emb": true, "position_embedding_xdrope": true, "max_position_embeddings": 262144, "rope_theta": 10000.0, "mlp_bias": false, "norm_type": "hf_rms", "anyres_pooling_size": 2, "anyres_vit_max_image_size": 2048, "anyres_vit_two_views": false, "perceive_pre_norm": true, "perceive_post_norm": true, "poolmlp": 0, "remove_prenorm": true, "two_view": true, "use_normalize_pool": false, "use_fusion_block": false, "use_layernorm": true }, "vit_add_patchemb_bias": true, "vit_input_resolution": 224, "vit_mapping_type": "simple_conv_mlp", "vit_norm_type": "fused", "vit_patch": 1, "vit_path": null, "vit_remove_prenorm": true, "vit_token": 58, "vit_type": "AnyResVit-tp", "vit_used_rms_norm": true, "vocab_size": 120818, "xdrope_section": [ 0.25, 0.25, 0.25, 0.25 ] }