Hugging Face's logo

belfner
/
vit_base_patch16_lingbot.robbyant

Image Feature Extraction
timm
PyTorch
Safetensors
Transformers
Model card Files
xet
 Community
vit_base_patch16_lingbot.robbyant
File size: 2,791 Bytes
5b7007f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
{
  "variant": "base",
  "arch": "vit_base_patch16_lingbot",
  "tag": "robbyant",
  "source_repo": "robbyant/lingbot-vision-vit-base",
  "source_revision": "f606f8c6c4002234ea68038f4d7c7cf57da96dfa",
  "source_sha256": "783dfb59014c34e9f0013db60bf6f5cc3c6b0604eb9528fb5df65e80769c5825",
  "wrapper_key": "model",
  "source_tensors": 188,
  "converted_tensors": 186,
  "param_count": 85659648,
  "dtypes": [
    "torch.float32"
  ],
  "save_dir": "/home/belfner/PycharmProjects/pytorch-image-models/converted/vit_base_patch16_lingbot.robbyant",
  "artifacts": {
    "config.json": "3c3d3969ac84f7a030cf3899a4947149607a6cfb249cd99548a664878294466c",
    "model.safetensors": "1242e170cef1bafeedc13ac039e9e42dacbb2881078bcc9417650e28bb9e06f7",
    "pytorch_model.bin": "8acbd811a656551113f5fe1a4d62980d8aad5bd44275d89bc449be83ca2c1f99",
    "README.md": "cd2172c0cd2e8fc5bc4712c7b9e0d9bbb5f27e89e0ee854eed70f8775767b4e2"
  },
  "parity": {
    "512x512": {
      "cls": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999998807907104
      },
      "registers": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999998807907104
      },
      "patches": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999997019767761
      }
    },
    "384x512": {
      "cls": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999998211860657
      },
      "registers": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999997019767761
      },
      "patches": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999995827674866
      }
    },
    "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": 0.9999997019767761
      },
      "registers": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999997019767761
      },
      "patches": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999996423721313
      }
    }
  },
  "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"
  }
}