| { |
| "architectures": [ |
| "Qwen3VLForConditionalGeneration" |
| ], |
| "bg_token_id": 151673, |
| "decoder_mode": "joint", |
| "dtype": "float32", |
| "eos_token_id": 151645, |
| "image_token_id": 151655, |
| "joint_exclude_bg": true, |
| "joint_focal_gamma": 2.0, |
| "joint_lambda_dice": 2.0, |
| "mask_decoder_config": { |
| "decoder_chunk_size": 8, |
| "dtype": "float32", |
| "mask_decoder_embedding_input_dim": 2560, |
| "mask_decoder_transformer_dim": 512, |
| "model_type": "qwen3_vl_mask_decoder", |
| "transformer_attention_downsample_rate": 1, |
| "transformer_depth": 4, |
| "transformer_embedding_dim": 512, |
| "transformer_mlp_dim": 2048, |
| "transformer_num_heads": 8, |
| "utonia_enc_channels": [ |
| 54, |
| 108, |
| 216, |
| 432, |
| 576 |
| ] |
| }, |
| "mask_decoder_fusion_mode": "concat", |
| "model_type": "qwen3_vl", |
| "pad_token_id": 151643, |
| "point_cloud_config": { |
| "ckpt_path": null, |
| "downsample_ratio": 20, |
| "drop_path_rate": 0.0, |
| "dtype": "float32", |
| "embed_dim": 64, |
| "geo_decoder_downsample_ratio": 1, |
| "geo_decoder_ln_post": true, |
| "geo_decoder_mlp_expand_ratio": 4, |
| "heads": 16, |
| "include_pi": false, |
| "label_type": "binary", |
| "model_type": "qwen3_vl_point_cloud", |
| "num_decoder_layers": 16, |
| "num_encoder_layers": 8, |
| "num_freqs": 8, |
| "num_latents": 4096, |
| "output_hidden_size": 2560, |
| "pc_sharpedge_size": 0, |
| "pc_size": 81920, |
| "point_feats": 4, |
| "qk_norm": true, |
| "qkv_bias": false, |
| "scale_factor": 1.0039506158752403, |
| "surface_extractor": null, |
| "use_ln_post": true, |
| "volume_decoder": null, |
| "width": 1024 |
| }, |
| "point_cloud_encoder_type": "utonia", |
| "point_cloud_end_token_id": 151670, |
| "point_cloud_start_token_id": 151669, |
| "point_cloud_token_id": 151671, |
| "seg_loss_weight": 1.0, |
| "seg_token_id": 151672, |
| "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": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 9728, |
| "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, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "4.57.3", |
| "use_mask_decoder": true, |
| "utonia_ckpt_path": null, |
| "utonia_enc_channels": [ |
| 54, |
| 108, |
| 216, |
| 432, |
| 576 |
| ], |
| "utonia_num_tokens": 4096, |
| "utonia_scale": 5.0, |
| "video_token_id": 151656, |
| "vision_config": { |
| "deepstack_visual_indexes": [ |
| 5, |
| 11, |
| 17 |
| ], |
| "depth": 24, |
| "dtype": "float32", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 1024, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "model_type": "qwen3_vl", |
| "num_heads": 16, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 2560, |
| "patch_size": 16, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 151653, |
| "vision_start_token_id": 151652 |
| } |
|
|
