Hugging Face's logo

huggingface-mic
/
clip-vit-base-patch32-mic

PyTorch
clip
mic
test-artifact
Model card Files
xet
 Community
2

Review cloud MIC baselines 7d8449a176b7481f9cb779992b3f8cb3

#1
by tarekziade HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+371
-175
Files changed (6) hide show
  1. integrations/transformers/expectations/cpu-x86_64-bf16/mic-clip-vit-base-patch32-slim.bfloat16.json +151 -0
  2. integrations/transformers/expectations/cpu-x86_64/mic-clip-vit-base-patch32-slim.eager.json +47 -38
  3. integrations/transformers/expectations/cpu-x86_64/mic-clip-vit-base-patch32-slim.json +43 -34
  4. integrations/transformers/expectations/cuda/mic-clip-vit-base-patch32-slim.bfloat16.json +32 -23
  5. integrations/transformers/expectations/cuda/mic-clip-vit-base-patch32-slim.eager.json +49 -40
  6. integrations/transformers/expectations/cuda/mic-clip-vit-base-patch32-slim.json +49 -40
integrations/transformers/expectations/cpu-x86_64-bf16/mic-clip-vit-base-patch32-slim.bfloat16.json ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "recorded_with": {
3
+ "contract": "huggingface-mic/clip-vit-base-patch32-mic",
4
+ "contract_name": "CLIP",
5
+ "contract_revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
6
+ "framework": "transformers",
7
+ "variant": "bfloat16",
8
+ "target": "mic-clip-vit-base-patch32-slim",
9
+ "kind": "fixture",
10
+ "revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
11
+ "environment": {
12
+ "python": "3.11.17",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cpu",
15
+ "torchvision": "0.29.1+cpu",
16
+ "torchaudio": "2.11.0+cpu",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.3.5",
19
+ "pillow": "12.3.0",
20
+ "accelerate": "1.15.0",
21
+ "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
+ "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.47,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cpu (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cpu (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.3.5 (pinned 1.26.4)",
35
+ "pillow": "12.3.0 (pinned 12.2.0)",
36
+ "accelerate": "1.15.0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
+ },
43
+ "platform": "cpu-x86_64-bf16"
44
+ },
45
+ "outputs": {
46
+ "runtime": {
47
+ "device": "cpu",
48
+ "dtype": "bfloat16",
49
+ "attn_implementation": "sdpa"
50
+ },
51
+ "image_to_text": [
52
+ 1,
53
+ 1,
54
+ 1,
55
+ 2
56
+ ],
57
+ "text_to_image": [
58
+ 1,
59
+ 1,
60
+ 1,
61
+ 1
62
+ ],
63
+ "logits_per_image": [
64
+ [
65
+ -2.609375,
66
+ -2.1875,
67
+ -2.484375,
68
+ -2.6875
69
+ ],
70
+ [
71
+ 4.1875,
72
+ 4.28125,
73
+ 4.25,
74
+ 3.8125
75
+ ],
76
+ [
77
+ 1.5546875,
78
+ 1.609375,
79
+ 1.2578125,
80
+ 1.2109375
81
+ ],
82
+ [
83
+ -0.423828125,
84
+ -0.26171875,
85
+ -0.1181640625,
86
+ -0.486328125
87
+ ]
88
+ ],
89
+ "text_kwargs_input_ids": [
90
+ [
91
+ 49406,
92
+ 320,
93
+ 1125,
94
+ 539,
95
+ 320,
96
+ 736,
97
+ 3999,
98
+ 49407
99
+ ],
100
+ [
101
+ 49406,
102
+ 320,
103
+ 1125,
104
+ 539,
105
+ 320,
106
+ 1901,
107
+ 3999,
108
+ 49407
109
+ ],
110
+ [
111
+ 49406,
112
+ 320,
113
+ 1125,
114
+ 539,
115
+ 320,
116
+ 1746,
117
+ 3999,
118
+ 49407
119
+ ],
120
+ [
121
+ 49406,
122
+ 320,
123
+ 1125,
124
+ 539,
125
+ 320,
126
+ 4481,
127
+ 3999,
128
+ 49407
129
+ ]
130
+ ],
131
+ "image_processor_config_keys": [
132
+ "crop_size",
133
+ "do_center_crop",
134
+ "do_normalize",
135
+ "do_resize",
136
+ "feature_extractor_type",
137
+ "image_mean",
138
+ "image_std",
139
+ "resample",
140
+ "size"
141
+ ],
142
+ "training": {
143
+ "loss": 2.53125,
144
+ "gradients": {
145
+ "visual_projection.weight": true,
146
+ "text_projection.weight": true
147
+ },
148
+ "updated": true
149
+ }
150
+ }
151
+ }
integrations/transformers/expectations/cpu-x86_64/mic-clip-vit-base-patch32-slim.eager.json CHANGED
@@ -1,36 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/CLIP-integration",
4
- "contract_revision": "cb2e2abc4c4c992c316ab40d4a3360b1e748fcfe",
 
5
  "framework": "transformers",
6
  "variant": "eager",
7
  "target": "mic-clip-vit-base-patch32-slim",
8
  "kind": "fixture",
9
- "revision": "adad0f30de071148ab0b55bb2263ac909e58cc5b",
10
  "environment": {
11
- "python": "3.10.22",
12
- "transformers": "5.19.0.dev0",
13
- "torch": "2.11.0+cpu",
14
- "torchvision": "0.26.0+cpu",
15
  "torchaudio": "2.11.0+cpu",
16
- "tokenizers": "0.23.1",
17
- "numpy": "1.26.4",
18
- "pillow": "12.2.0",
19
- "accelerate": "1.13.0",
20
  "safetensors": "0.8.0",
21
- "huggingface-hub": "1.32.0",
22
- "sentencepiece": "0.2.1",
23
- "protobuf": "6.33.6",
24
  "librosa": "0.11.0",
25
- "soundfile": "0.13.1",
26
- "scipy": "1.15.3",
27
- "local_patches": [
28
- "config-field-generation-params",
29
- "masked-spec-embed-init",
30
- "whisper-decode-tensor-batch"
31
- ]
 
 
 
 
 
 
 
 
 
32
  },
33
- "seconds": 3.59,
34
  "platform": "cpu-x86_64"
35
  },
36
  "outputs": {
@@ -53,28 +62,28 @@
53
  ],
54
  "logits_per_image": [
55
  [
56
- -2.637209892272949,
57
- -2.2477338314056396,
58
- -2.5039865970611572,
59
- -2.7232155799865723
60
  ],
61
  [
62
  4.1433186531066895,
63
- 4.256855010986328,
64
- 4.226871490478516,
65
- 3.7787840366363525
66
  ],
67
  [
68
- 1.5251166820526123,
69
- 1.6053072214126587,
70
- 1.22788667678833,
71
- 1.1937217712402344
72
  ],
73
  [
74
- -0.4373687207698822,
75
- -0.2958236634731293,
76
- -0.10970804840326309,
77
- -0.473240464925766
78
  ]
79
  ],
80
  "text_kwargs_input_ids": [
@@ -131,7 +140,7 @@
131
  "size"
132
  ],
133
  "training": {
134
- "loss": 2.5255932807922363,
135
  "gradients": {
136
  "visual_projection.weight": true,
137
  "text_projection.weight": true
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/clip-vit-base-patch32-mic",
4
+ "contract_name": "CLIP",
5
+ "contract_revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
6
  "framework": "transformers",
7
  "variant": "eager",
8
  "target": "mic-clip-vit-base-patch32-slim",
9
  "kind": "fixture",
10
+ "revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
11
  "environment": {
12
+ "python": "3.11.17",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cpu",
15
+ "torchvision": "0.29.1+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.3.5",
19
+ "pillow": "12.3.0",
20
+ "accelerate": "1.15.0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.51,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cpu (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cpu (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.3.5 (pinned 1.26.4)",
35
+ "pillow": "12.3.0 (pinned 12.2.0)",
36
+ "accelerate": "1.15.0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cpu-x86_64"
44
  },
45
  "outputs": {
 
62
  ],
63
  "logits_per_image": [
64
  [
65
+ -2.6372082233428955,
66
+ -2.2477328777313232,
67
+ -2.5039870738983154,
68
+ -2.7232184410095215
69
  ],
70
  [
71
  4.1433186531066895,
72
+ 4.2568535804748535,
73
+ 4.226871967315674,
74
+ 3.778783082962036
75
  ],
76
  [
77
+ 1.5251171588897705,
78
+ 1.60530686378479,
79
+ 1.2278860807418823,
80
+ 1.1937216520309448
81
  ],
82
  [
83
+ -0.437367707490921,
84
+ -0.29582342505455017,
85
+ -0.10970768332481384,
86
+ -0.4732420742511749
87
  ]
88
  ],
89
  "text_kwargs_input_ids": [
 
140
  "size"
141
  ],
142
  "training": {
143
+ "loss": 2.5255935192108154,
144
  "gradients": {
145
  "visual_projection.weight": true,
146
  "text_projection.weight": true
integrations/transformers/expectations/cpu-x86_64/mic-clip-vit-base-patch32-slim.json CHANGED
@@ -1,36 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/CLIP-integration",
4
- "contract_revision": "cb2e2abc4c4c992c316ab40d4a3360b1e748fcfe",
 
5
  "framework": "transformers",
6
  "variant": "default",
7
  "target": "mic-clip-vit-base-patch32-slim",
8
  "kind": "fixture",
9
- "revision": "adad0f30de071148ab0b55bb2263ac909e58cc5b",
10
  "environment": {
11
- "python": "3.10.22",
12
- "transformers": "5.19.0.dev0",
13
- "torch": "2.11.0+cpu",
14
- "torchvision": "0.26.0+cpu",
15
  "torchaudio": "2.11.0+cpu",
16
- "tokenizers": "0.23.1",
17
- "numpy": "1.26.4",
18
- "pillow": "12.2.0",
19
- "accelerate": "1.13.0",
20
  "safetensors": "0.8.0",
21
- "huggingface-hub": "1.32.0",
22
- "sentencepiece": "0.2.1",
23
- "protobuf": "6.33.6",
24
  "librosa": "0.11.0",
25
- "soundfile": "0.13.1",
26
- "scipy": "1.15.3",
27
- "local_patches": [
28
- "config-field-generation-params",
29
- "masked-spec-embed-init",
30
- "whisper-decode-tensor-batch"
31
- ]
 
 
 
 
 
 
 
 
 
32
  },
33
- "seconds": 3.69,
34
  "platform": "cpu-x86_64"
35
  },
36
  "outputs": {
@@ -54,27 +63,27 @@
54
  "logits_per_image": [
55
  [
56
  -2.637209892272949,
57
- -2.2477328777313232,
58
  -2.503986358642578,
59
- -2.723217487335205
60
  ],
61
  [
62
  4.143317222595215,
63
- 4.256854057312012,
64
  4.226871013641357,
65
- 3.778783082962036
66
  ],
67
  [
68
- 1.5251176357269287,
69
- 1.6053062677383423,
70
- 1.2278861999511719,
71
- 1.1937217712402344
72
  ],
73
  [
74
- -0.4373680353164673,
75
- -0.2958209812641144,
76
- -0.10970687866210938,
77
- -0.4732409119606018
78
  ]
79
  ],
80
  "text_kwargs_input_ids": [
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/clip-vit-base-patch32-mic",
4
+ "contract_name": "CLIP",
5
+ "contract_revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
6
  "framework": "transformers",
7
  "variant": "default",
8
  "target": "mic-clip-vit-base-patch32-slim",
9
  "kind": "fixture",
10
+ "revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
11
  "environment": {
12
+ "python": "3.11.17",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cpu",
15
+ "torchvision": "0.29.1+cpu",
16
  "torchaudio": "2.11.0+cpu",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.3.5",
19
+ "pillow": "12.3.0",
20
+ "accelerate": "1.15.0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.45,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cpu (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cpu (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.3.5 (pinned 1.26.4)",
35
+ "pillow": "12.3.0 (pinned 12.2.0)",
36
+ "accelerate": "1.15.0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cpu-x86_64"
44
  },
45
  "outputs": {
 
63
  "logits_per_image": [
64
  [
65
  -2.637209892272949,
66
+ -2.2477335929870605,
67
  -2.503986358642578,
68
+ -2.7232167720794678
69
  ],
70
  [
71
  4.143317222595215,
72
+ 4.2568535804748535,
73
  4.226871013641357,
74
+ 3.7787840366363525
75
  ],
76
  [
77
+ 1.5251173973083496,
78
+ 1.6053072214126587,
79
+ 1.2278858423233032,
80
+ 1.1937224864959717
81
  ],
82
  [
83
+ -0.4373682141304016,
84
+ -0.2958228290081024,
85
+ -0.10970722883939743,
86
+ -0.4732404351234436
87
  ]
88
  ],
89
  "text_kwargs_input_ids": [
integrations/transformers/expectations/cuda/mic-clip-vit-base-patch32-slim.bfloat16.json CHANGED
@@ -1,36 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/CLIP-integration",
4
- "contract_revision": "cb2e2abc4c4c992c316ab40d4a3360b1e748fcfe",
 
5
  "framework": "transformers",
6
  "variant": "bfloat16",
7
  "target": "mic-clip-vit-base-patch32-slim",
8
  "kind": "fixture",
9
- "revision": "adad0f30de071148ab0b55bb2263ac909e58cc5b",
10
  "environment": {
11
- "python": "3.10.12",
12
- "transformers": "5.19.0.dev0",
13
- "torch": "2.11.0+cu128",
14
- "torchvision": "0.26.0+cu128",
15
- "torchaudio": "2.11.0+cu128",
16
- "tokenizers": "0.23.1",
17
- "numpy": "1.26.4",
18
- "pillow": "12.2.0",
19
- "accelerate": "1.13.0",
20
  "safetensors": "0.8.0",
21
- "huggingface-hub": "1.32.0",
22
- "sentencepiece": "0.2.1",
23
- "protobuf": "6.33.6",
24
  "librosa": "0.11.0",
25
- "soundfile": "0.13.1",
26
- "scipy": "1.15.3",
27
- "local_patches": [
28
- "config-field-generation-params",
29
- "masked-spec-embed-init",
30
- "whisper-decode-tensor-batch"
31
- ]
 
 
 
 
 
 
 
 
 
32
  },
33
- "seconds": 7.75,
34
  "platform": "cuda"
35
  },
36
  "outputs": {
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/clip-vit-base-patch32-mic",
4
+ "contract_name": "CLIP",
5
+ "contract_revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
6
  "framework": "transformers",
7
  "variant": "bfloat16",
8
  "target": "mic-clip-vit-base-patch32-slim",
9
  "kind": "fixture",
10
+ "revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
11
  "environment": {
12
+ "python": "3.11.18",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cu130",
15
+ "torchvision": "0.29.1+cu130",
16
+ "torchaudio": "2.11.0+cu130",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.4.6",
19
+ "pillow": "13.0.0",
20
+ "accelerate": "1.16.0.dev0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.16,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cu130 (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cu130 (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.4.6 (pinned 1.26.4)",
35
+ "pillow": "13.0.0 (pinned 12.2.0)",
36
+ "accelerate": "1.16.0.dev0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cuda"
44
  },
45
  "outputs": {
integrations/transformers/expectations/cuda/mic-clip-vit-base-patch32-slim.eager.json CHANGED
@@ -1,36 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/CLIP-integration",
4
- "contract_revision": "cb2e2abc4c4c992c316ab40d4a3360b1e748fcfe",
 
5
  "framework": "transformers",
6
  "variant": "eager",
7
  "target": "mic-clip-vit-base-patch32-slim",
8
  "kind": "fixture",
9
- "revision": "adad0f30de071148ab0b55bb2263ac909e58cc5b",
10
  "environment": {
11
- "python": "3.10.12",
12
- "transformers": "5.19.0.dev0",
13
- "torch": "2.11.0+cu128",
14
- "torchvision": "0.26.0+cu128",
15
- "torchaudio": "2.11.0+cu128",
16
- "tokenizers": "0.23.1",
17
- "numpy": "1.26.4",
18
- "pillow": "12.2.0",
19
- "accelerate": "1.13.0",
20
  "safetensors": "0.8.0",
21
- "huggingface-hub": "1.32.0",
22
- "sentencepiece": "0.2.1",
23
- "protobuf": "6.33.6",
24
  "librosa": "0.11.0",
25
- "soundfile": "0.13.1",
26
- "scipy": "1.15.3",
27
- "local_patches": [
28
- "config-field-generation-params",
29
- "masked-spec-embed-init",
30
- "whisper-decode-tensor-batch"
31
- ]
 
 
 
 
 
 
 
 
 
32
  },
33
- "seconds": 7.55,
34
  "platform": "cuda"
35
  },
36
  "outputs": {
@@ -53,28 +62,28 @@
53
  ],
54
  "logits_per_image": [
55
  [
56
- -2.637207269668579,
57
- -2.2477309703826904,
58
- -2.503983736038208,
59
- -2.7232158184051514
60
  ],
61
  [
62
- 4.143322944641113,
63
- 4.256857395172119,
64
- 4.226873397827148,
65
- 3.778785228729248
66
  ],
67
  [
68
- 1.5251175165176392,
69
- 1.605304479598999,
70
- 1.2278834581375122,
71
- 1.193720817565918
72
  ],
73
  [
74
- -0.4373661279678345,
75
- -0.29582053422927856,
76
- -0.10970576852560043,
77
- -0.4732407331466675
78
  ]
79
  ],
80
  "text_kwargs_input_ids": [
@@ -131,7 +140,7 @@
131
  "size"
132
  ],
133
  "training": {
134
- "loss": 2.525594711303711,
135
  "gradients": {
136
  "visual_projection.weight": true,
137
  "text_projection.weight": true
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/clip-vit-base-patch32-mic",
4
+ "contract_name": "CLIP",
5
+ "contract_revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
6
  "framework": "transformers",
7
  "variant": "eager",
8
  "target": "mic-clip-vit-base-patch32-slim",
9
  "kind": "fixture",
10
+ "revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
11
  "environment": {
12
+ "python": "3.11.18",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cu130",
15
+ "torchvision": "0.29.1+cu130",
16
+ "torchaudio": "2.11.0+cu130",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.4.6",
19
+ "pillow": "13.0.0",
20
+ "accelerate": "1.16.0.dev0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.06,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cu130 (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cu130 (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.4.6 (pinned 1.26.4)",
35
+ "pillow": "13.0.0 (pinned 12.2.0)",
36
+ "accelerate": "1.16.0.dev0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cuda"
44
  },
45
  "outputs": {
 
62
  ],
63
  "logits_per_image": [
64
  [
65
+ -2.636889696121216,
66
+ -2.2474372386932373,
67
+ -2.5036959648132324,
68
+ -2.7229273319244385
69
  ],
70
  [
71
+ 4.142627716064453,
72
+ 4.256189346313477,
73
+ 4.226197719573975,
74
+ 3.7780885696411133
75
  ],
76
  [
77
+ 1.5253466367721558,
78
+ 1.6054904460906982,
79
+ 1.228113055229187,
80
+ 1.193971037864685
81
  ],
82
  [
83
+ -0.4384934604167938,
84
+ -0.2969169318675995,
85
+ -0.1108640506863594,
86
+ -0.47429358959198
87
  ]
88
  ],
89
  "text_kwargs_input_ids": [
 
140
  "size"
141
  ],
142
  "training": {
143
+ "loss": 2.5254127979278564,
144
  "gradients": {
145
  "visual_projection.weight": true,
146
  "text_projection.weight": true
integrations/transformers/expectations/cuda/mic-clip-vit-base-patch32-slim.json CHANGED
@@ -1,36 +1,45 @@
1
  {
2
  "recorded_with": {
3
- "contract": "hf-internal-testing/CLIP-integration",
4
- "contract_revision": "cb2e2abc4c4c992c316ab40d4a3360b1e748fcfe",
 
5
  "framework": "transformers",
6
  "variant": "default",
7
  "target": "mic-clip-vit-base-patch32-slim",
8
  "kind": "fixture",
9
- "revision": "adad0f30de071148ab0b55bb2263ac909e58cc5b",
10
  "environment": {
11
- "python": "3.10.12",
12
- "transformers": "5.19.0.dev0",
13
- "torch": "2.11.0+cu128",
14
- "torchvision": "0.26.0+cu128",
15
- "torchaudio": "2.11.0+cu128",
16
- "tokenizers": "0.23.1",
17
- "numpy": "1.26.4",
18
- "pillow": "12.2.0",
19
- "accelerate": "1.13.0",
20
  "safetensors": "0.8.0",
21
- "huggingface-hub": "1.32.0",
22
- "sentencepiece": "0.2.1",
23
- "protobuf": "6.33.6",
24
  "librosa": "0.11.0",
25
- "soundfile": "0.13.1",
26
- "scipy": "1.15.3",
27
- "local_patches": [
28
- "config-field-generation-params",
29
- "masked-spec-embed-init",
30
- "whisper-decode-tensor-batch"
31
- ]
 
 
 
 
 
 
 
 
 
32
  },
33
- "seconds": 7.58,
34
  "platform": "cuda"
35
  },
36
  "outputs": {
@@ -53,28 +62,28 @@
53
  ],
54
  "logits_per_image": [
55
  [
56
- -2.6372063159942627,
57
- -2.247730016708374,
58
- -2.5039823055267334,
59
- -2.723214864730835
60
  ],
61
  [
62
- 4.1433210372924805,
63
- 4.25685453414917,
64
- 4.22687292098999,
65
- 3.778785228729248
66
  ],
67
  [
68
- 1.525118112564087,
69
- 1.6053059101104736,
70
- 1.2278845310211182,
71
- 1.193721890449524
72
  ],
73
  [
74
- -0.43736541271209717,
75
- -0.29581987857818604,
76
- -0.10970433056354523,
77
- -0.4732396602630615
78
  ]
79
  ],
80
  "text_kwargs_input_ids": [
@@ -131,7 +140,7 @@
131
  "size"
132
  ],
133
  "training": {
134
- "loss": 2.525594472885132,
135
  "gradients": {
136
  "visual_projection.weight": true,
137
  "text_projection.weight": true
 
1
  {
2
  "recorded_with": {
3
+ "contract": "huggingface-mic/clip-vit-base-patch32-mic",
4
+ "contract_name": "CLIP",
5
+ "contract_revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
6
  "framework": "transformers",
7
  "variant": "default",
8
  "target": "mic-clip-vit-base-patch32-slim",
9
  "kind": "fixture",
10
+ "revision": "5eb92c4457ab608437d2a495fbed71df19740da8",
11
  "environment": {
12
+ "python": "3.11.18",
13
+ "transformers": "5.21.0.dev0",
14
+ "torch": "2.14.0+cu130",
15
+ "torchvision": "0.29.1+cu130",
16
+ "torchaudio": "2.11.0+cu130",
17
+ "tokenizers": "0.23.3",
18
+ "numpy": "2.4.6",
19
+ "pillow": "13.0.0",
20
+ "accelerate": "1.16.0.dev0",
21
  "safetensors": "0.8.0",
22
+ "huggingface-hub": "2.3.0",
23
+ "sentencepiece": "0.2.2",
24
+ "protobuf": "7.36.2",
25
  "librosa": "0.11.0",
26
+ "soundfile": "0.14.0",
27
+ "scipy": "1.17.1"
28
+ },
29
+ "seconds": 7.08,
30
+ "environment_differs": {
31
+ "torch": "2.14.0+cu130 (pinned 2.11.0)",
32
+ "torchvision": "0.29.1+cu130 (pinned 0.26.0)",
33
+ "tokenizers": "0.23.3 (pinned 0.23.1)",
34
+ "numpy": "2.4.6 (pinned 1.26.4)",
35
+ "pillow": "13.0.0 (pinned 12.2.0)",
36
+ "accelerate": "1.16.0.dev0 (pinned 1.13.0)",
37
+ "huggingface-hub": "2.3.0 (pinned 1.32.0)",
38
+ "sentencepiece": "0.2.2 (pinned 0.2.1)",
39
+ "protobuf": "7.36.2 (pinned 6.33.6)",
40
+ "soundfile": "0.14.0 (pinned 0.13.1)",
41
+ "scipy": "1.17.1 (pinned 1.15.3)"
42
  },
 
43
  "platform": "cuda"
44
  },
45
  "outputs": {
 
62
  ],
63
  "logits_per_image": [
64
  [
65
+ -2.6368887424468994,
66
+ -2.247436285018921,
67
+ -2.5036942958831787,
68
+ -2.722926616668701
69
  ],
70
  [
71
+ 4.142626762390137,
72
+ 4.256187438964844,
73
+ 4.226197242736816,
74
+ 3.7780885696411133
75
  ],
76
  [
77
+ 1.525346040725708,
78
+ 1.6054904460906982,
79
+ 1.2281131744384766,
80
+ 1.193971037864685
81
  ],
82
  [
83
+ -0.43849292397499084,
84
+ -0.2969170808792114,
85
+ -0.11086298525333405,
86
+ -0.4742926359176636
87
  ]
88
  ],
89
  "text_kwargs_input_ids": [
 
140
  "size"
141
  ],
142
  "training": {
143
+ "loss": 2.5254125595092773,
144
  "gradients": {
145
  "visual_projection.weight": true,
146
  "text_projection.weight": true