Add converted LingBot-Vision weights

README.md

@@ -0,0 +1,145 @@
+---
+tags:
+- image-feature-extraction
+- timm
+- transformers
+pipeline_tag: image-feature-extraction
+library_name: timm
+license: apache-2.0
+---
+# Model card for vit_small_patch16_lingbot.robbyant
+
+A LingBot-Vision ViT-Small/16 image feature encoder. Distilled from the masked-boundary-pretrained ViT-Giant/16 teacher by the paper authors
+and converted to timm's Eva/DINOv3 implementation.
+
+## Model Notes
+* Token layout: CLS at index 0, four register tokens at indices 1-4, patch tokens thereafter.
+  The pretrained cfg uses `global_pool='avg'` over patch tokens; pass `global_pool='token'` at
+  creation to reproduce the upstream CLS representation.
+* fp32 forward outputs match the reference implementation with max abs diff 0.0e+00 on CLS,
+  register, and patch tokens at 512x512 and 384x512. Conversion provenance, the pinned source
+  revision, and per-partition parity metrics are recorded in `manifest.json`.
+* Converted from https://huggingface.co/robbyant/lingbot-vision-vit-small at revision `127cbcec380d`.
+  The `vit_small_patch16_lingbot.robbyant` architecture is pending in timm (PR); its pretrained cfg resolves the weights
+  from this repo, so the usage below works on a timm checkout that includes the LingBot entrypoints.
+
+## Model Details
+- **Model Type:** Image Feature Encoder
+- **Model Stats:**
+  - Params (M): 21.6
+  - GMACs: 22.2
+  - Activations (M): 43.07
+  - Image size: 512 x 512
+- **Original:** https://github.com/robbyant/lingbot-vision
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
+- **Pretrain Dataset:** 161M-image curated web corpus (see paper)
+- **Papers:**
+  - Vision Pretraining for Dense Spatial Perception: https://arxiv.org/abs/2607.05247
+  - PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
+
+## Model Usage
+### Image Classification
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+import torch
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model('vit_small_patch16_lingbot.robbyant', pretrained=True)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
+
+top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
+```
+
+### Feature Map Extraction
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'vit_small_patch16_lingbot.robbyant',
+    pretrained=True,
+    features_only=True,
+)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1
+
+for o in output:
+    # print shape of each feature map in output
+    print(o.shape)
+```
+
+### Image Embeddings
+```python
+from urllib.request import urlopen
+from PIL import Image
+import timm
+
+img = Image.open(urlopen(
+    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
+))
+
+model = timm.create_model(
+    'vit_small_patch16_lingbot.robbyant',
+    pretrained=True,
+    num_classes=0,  # remove classifier nn.Linear
+)
+model = model.eval()
+
+# get model specific transforms (normalization, resize)
+data_config = timm.data.resolve_model_data_config(model)
+transforms = timm.data.create_transform(**data_config, is_training=False)
+
+output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
+
+# or equivalently (without needing to set num_classes=0)
+output = model.forward_features(transforms(img).unsqueeze(0))
+# output is unpooled, a (1, 1029, 384) shaped tensor
+
+output = model.forward_head(output, pre_logits=True)
+# output is a (1, num_features) shaped tensor
+```
+
+## Model Comparison
+Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
+
+## Citation
+```bibtex
+@article{lingbot-vision2026,
+  title={Vision Pretraining for Dense Spatial Perception},
+  author={Fu, Zelin and Tan, Bin and Sun, Changjiang and Liu, Shaohui and Zheng, Kecheng and Xu, Yinghao and Zhu, Xing and Shen, Yujun and Xue, Nan},
+  journal={arXiv preprint arXiv:2607.05247},
+  year={2026}
+}
+```
+```bibtex
+@misc{rw2019timm,
+  author = {Ross Wightman},
+  title = {PyTorch Image Models},
+  year = {2019},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  doi = {10.5281/zenodo.4414861},
+  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
+}
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "architecture": "vit_small_patch16_lingbot",
+  "num_classes": 0,
+  "num_features": 384,
+  "global_pool": "avg",
+  "pretrained_cfg": {
+    "tag": "robbyant",
+    "custom_load": false,
+    "input_size": [
+      3,
+      512,
+      512
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bilinear",
+    "crop_pct": 1.0,
+    "crop_mode": "squash",
+    "mean": [
+      0.485,
+      0.456,
+      0.406
+    ],
+    "std": [
+      0.229,
+      0.224,
+      0.225
+    ],
+    "num_classes": 0,
+    "pool_size": null,
+    "first_conv": "patch_embed.proj",
+    "classifier": "head",
+    "license": "apache-2.0",
+    "origin_url": "https://github.com/robbyant/lingbot-vision",
+    "paper_ids": "arXiv:2607.05247"
+  }
+}

manifest.json

@@ -0,0 +1,94 @@
+{
+  "variant": "small",
+  "arch": "vit_small_patch16_lingbot",
+  "tag": "robbyant",
+  "source_repo": "robbyant/lingbot-vision-vit-small",
+  "source_revision": "127cbcec380de0bcd55bdc1b1fad3819850a6514",
+  "source_sha256": "dca36562cb6b0b34504df6edc18fa282c5ef06fb375c3e91d5487247a1096f9d",
+  "wrapper_key": "model",
+  "source_tensors": 188,
+  "converted_tensors": 186,
+  "param_count": 21596160,
+  "dtypes": [
+    "torch.float32"
+  ],
+  "save_dir": "/home/belfner/PycharmProjects/pytorch-image-models/converted/vit_small_patch16_lingbot.robbyant",
+  "artifacts": {
+    "config.json": "2262dd5a2bd838c83671a33638894af6711712f1f04b6c8ba1a39df8779e5a04",
+    "model.safetensors": "f879b5b2352b0925d9ec12bdbfdbfeea4973ea0190f3a80232a9a451bbf895ee",
+    "pytorch_model.bin": "1ee09c96c84d9d7fb3332f41984da1b0083f78438652ce1ba02179074082d4cf",
+    "README.md": "11ee10680d95dda5f1368bc9f1b68cee14c448cb7af908dbf67fdf65fe620f06"
+  },
+  "parity": {
+    "512x512": {
+      "cls": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 1.0
+      },
+      "registers": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 1.0
+      },
+      "patches": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 0.9999997615814209
+      }
+    },
+    "384x512": {
+      "cls": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 1.0000001192092896
+      },
+      "registers": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 0.9999999403953552
+      },
+      "patches": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 0.9999997615814209
+      }
+    },
+    "public_forward_token_pool": {
+      "max_abs": 0.0
+    },
+    "public_forward_avg_pool_smoke": "pass",
+    "transform_max_abs": 0.0,
+    "real_image": {
+      "cls": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 1.0
+      },
+      "registers": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 0.9999999403953552
+      },
+      "patches": {
+        "max_abs": 0.0,
+        "mean_abs": 0.0,
+        "cos_min": 0.9999997019767761
+      }
+    }
+  },
+  "provenance": {
+    "converter_sha256": "166732a819c7af4542c50477c5ceeb01f3dc20061fef300f6a4fc437df48640c",
+    "timm_root": "/home/belfner/PycharmProjects/pytorch-image-models",
+    "timm_commit": "1fb842c917df1edd3c4a7c17edc4fc5588452cc5",
+    "timm_dirty": false,
+    "reference_root": "/home/belfner/PycharmProjects/pytorch-image-models/lingbot-vision",
+    "reference_commit": "151e46321bae4399f8568829f190c7bdec216b49",
+    "reference_dirty": false,
+    "torch": "2.13.0+cu130",
+    "timm_version": "1.0.29.dev0",
+    "safetensors": "0.8.0",
+    "huggingface_hub": "1.25.1",
+    "python": "3.14.0"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f879b5b2352b0925d9ec12bdbfdbfeea4973ea0190f3a80232a9a451bbf895ee
+size 86401352

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ee09c96c84d9d7fb3332f41984da1b0083f78438652ce1ba02179074082d4cf
+size 86451723