| { | |
| "architectures": ["Talk2DINO"], | |
| "model_type": "talk2dino", | |
| "auto_map": { | |
| "AutoConfig": "configuration_talk2dino.Talk2DINOConfig", | |
| "AutoModel": "modeling_talk2dino.Talk2DINO" | |
| }, | |
| "avg_self_attn_token": false, | |
| "clip_model_name": "ViT-B/16", | |
| "disentangled_self_attn_token": true, | |
| "is_eval": true, | |
| "keep_cls": false, | |
| "keep_end_seq": false, | |
| "loss": null, | |
| "model_name": "dinov2_vitl14_reg", | |
| "pre_trained": true, | |
| "proj_class": "vitl_mlp_infonce", | |
| "proj_model": "ProjectionLayer", | |
| "proj_name": "vitl_mlp_infonce", | |
| "resize_dim": 518, | |
| "type": "DINOText", | |
| "unfreeze_last_image_layer": false, | |
| "unfreeze_last_text_layer": false, | |
| "use_avg_text_token": false, | |
| "with_bg_clean": false | |
| } |