Hugging Face's logo

belfner
/
vit_large_patch16_lingbot.robbyant

Image Feature Extraction
timm
PyTorch
Safetensors
Transformers
Model card Files
xet
 Community
vit_large_patch16_lingbot.robbyant
File size: 2,796 Bytes
cc6bf2c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "large",
  "arch": "vit_large_patch16_lingbot",
  "tag": "robbyant",
  "source_repo": "robbyant/lingbot-vision-vit-large",
  "source_revision": "5e0370623d4fa5db945d00bc47a8545eed407d6b",
  "source_sha256": "5b5eb67ebbf990b747658ecf90f1cf2b93f5b0e8dfdfbceb060ae1fc364deb8f",
  "wrapper_key": "model",
  "source_tensors": 368,
  "converted_tensors": 366,
  "param_count": 303128576,
  "dtypes": [
    "torch.float32"
  ],
  "save_dir": "/home/belfner/PycharmProjects/pytorch-image-models/converted/vit_large_patch16_lingbot.robbyant",
  "artifacts": {
    "config.json": "f049966a00f9f2b274cfa507ca4616ac45f7033c364686250d1e5da647ba97b4",
    "model.safetensors": "2b269b4b82bed00ec27bde6ac0340f73ce6fe4e611ffa4551247f1d70592509e",
    "pytorch_model.bin": "b8a7ccc65491d472fdfc131ed1bf29316ca229920920821b8762525a9b885690",
    "README.md": "a540bbb1640b5dc2e79b197f53a87155d55805cc873eef5ccc7ed534de972d6c"
  },
  "parity": {
    "512x512": {
      "cls": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999998211860657
      },
      "registers": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999997615814209
      },
      "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": 1.0000001192092896
      },
      "registers": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999997615814209
      },
      "patches": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999997019767761
      }
    },
    "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": 0.9999999403953552
      },
      "registers": {
        "max_abs": 0.0,
        "mean_abs": 0.0,
        "cos_min": 0.9999995231628418
      },
      "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"
  }
}