Image Segmentation
Transformers
Safetensors
concor1
feature-extraction
vision-language-grounding
concept-correspondence
referring-expression-segmentation
phrase-grounding
open-vocabulary-segmentation
custom_code
Instructions to use UWGZQ/ConCor-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UWGZQ/ConCor-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="UWGZQ/ConCor-1", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("UWGZQ/ConCor-1", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "ConCor1ForConceptCorrespondence" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_concor1.ConCor1Config", | |
| "AutoModel": "modeling_concor1.ConCor1ForConceptCorrespondence", | |
| "AutoProcessor": "processing_concor1.ConCor1Processor" | |
| }, | |
| "backbone_config": { | |
| "image_token_id": 248056, | |
| "model_type": "qwen3_5", | |
| "text_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3584, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "linear_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 16, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 8, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": true, | |
| "use_cache": true, | |
| "vocab_size": 248462 | |
| }, | |
| "tie_word_embeddings": true, | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "architectures": null, | |
| "chunk_size_feed_forward": 0, | |
| "deepstack_visual_indexes": [], | |
| "depth": 12, | |
| "dtype": null, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "model_type": "qwen3_5", | |
| "num_heads": 12, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 1024, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "patch_size": 16, | |
| "problem_type": null, | |
| "return_dict": true, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053, | |
| "vocab_size": 248462 | |
| }, | |
| "bidirectional_full_attention": true, | |
| "bridge_grid_levels": [ | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10 | |
| ], | |
| "bridge_token_id_start": 248077, | |
| "correspondence_dim": 256, | |
| "dtype": "bfloat16", | |
| "fuse_vision_encoder_features": true, | |
| "image_max_pixels": 1003520, | |
| "image_min_pixels": 1003520, | |
| "image_threshold": 0.45, | |
| "merge_size": 2, | |
| "model_type": "concor1", | |
| "nms_iou_threshold": 0.5, | |
| "num_bridge_tokens": 385, | |
| "num_mask_upsample_blocks": 2, | |
| "patch_size": 16, | |
| "presence_hidden_dim": 256, | |
| "presence_threshold": 0.1, | |
| "text_threshold": 0.45, | |
| "transformers_version": "5.3.0" | |
| } | |