Hugging Face's logo

huggingface-mic
/
bert-mic

Safetensors
bert
mic
test-artifact
Model card Files
xet
 Community
1
tarekziade HF Staff commited on
Commit
55802f5
·
verified ·
1 Parent(s): 79d9d00

Keep the real checkpoint's weight names, prefix and file format (tensors unchanged; reload verified bit-exact)

Browse files
Files changed (2) hide show
  1. build.json +127 -119
  2. model.safetensors +2 -2
build.json CHANGED
@@ -1,126 +1,134 @@
1
  {
2
- "fixture": "hf-internal-testing/mic-bert-slim",
3
- "key": "7ce74647df48e43332a1634bb3c9c123e2845de5a9401b574555e1964f417d11",
4
- "key_fields": {
5
- "architectures": [
6
- "BertForMaskedLM"
7
- ],
8
- "output_hidden_states": false,
9
- "return_dict": true,
10
- "chunk_size_feed_forward": 0,
11
- "is_encoder_decoder": false,
12
- "id2label": {
13
- "0": "LABEL_0",
14
- "1": "LABEL_1"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  },
16
- "label2id": {
17
- "LABEL_0": 0,
18
- "LABEL_1": 1
19
  },
20
- "problem_type": null,
21
- "vocab_size": 30522,
22
- "hidden_size": 64,
23
- "num_hidden_layers": 2,
24
- "num_attention_heads": 4,
25
- "intermediate_size": 128,
26
- "hidden_act": "gelu",
27
- "hidden_dropout_prob": 0.1,
28
- "attention_probs_dropout_prob": 0.1,
29
- "max_position_embeddings": 512,
30
- "type_vocab_size": 2,
31
- "initializer_range": 0.02,
32
- "layer_norm_eps": 1e-12,
33
- "pad_token_id": 0,
34
- "use_cache": true,
35
- "classifier_dropout": null,
36
- "is_decoder": false,
37
- "add_cross_attention": false,
38
- "bos_token_id": null,
39
- "eos_token_id": null,
40
- "tie_word_embeddings": true,
41
- "gradient_checkpointing": false,
42
- "model_type": "bert",
43
- "position_embedding_type": "absolute",
44
- "output_attentions": false
45
- },
46
- "covers": {
47
- "google-bert/bert-base-uncased": "86b5e0934494bd15c9632b12f734a8a67f723594"
48
- },
49
- "built_from": {
50
- "repo": "google-bert/bert-base-uncased",
51
- "revision": "86b5e0934494bd15c9632b12f734a8a67f723594"
52
- },
53
- "seed": 17,
54
- "dtype": "float32",
55
- "builder": "example/build_fixtures.py",
56
- "model_class": "BertForMaskedLM",
57
- "parameters": 2088186,
58
- "missing_parameters": [],
59
- "checkpoint_inspection": "parameter metadata",
60
- "captured": {
61
- "call": "training step",
62
- "inputs": [
63
- "attention_mask",
64
- "input_ids",
65
- "labels",
66
- "token_type_ids"
67
- ]
68
- },
69
- "weights": "random",
70
- "gate": {
71
- "random": {
72
- "pass": true,
73
- "accepted_insensitive": {},
74
- "threshold": 0.001,
75
- "deltas": {
76
- "input_ids:roll_batch": 0.720638632774353,
77
- "input_ids:reverse": 0.7979322671890259,
78
- "token_type_ids:all_ones": 0.7735698223114014,
79
- "attention_mask:all_ones": 0.0027810335159301758
80
- },
81
- "weakest": "attention_mask:all_ones",
82
- "no_perturbation_defined": []
83
- }
84
- },
85
- "numeric_health": {
86
- "float32": {
87
- "outputs_finite": true,
88
- "loss_finite": true,
89
- "gradients_finite": true,
90
- "finite": true
91
  },
92
- "bfloat16": {
93
- "outputs_finite": true,
94
- "loss_finite": true,
95
- "gradients_finite": true,
96
- "finite": true
 
 
97
  },
98
- "float16": {
99
- "outputs_finite": true,
100
- "loss_finite": true,
101
- "gradients_finite": true,
102
- "finite": true
 
 
103
  }
104
- },
105
- "copied_unchanged": [
106
- "LICENSE",
107
- "tokenizer.json",
108
- "tokenizer_config.json",
109
- "vocab.txt"
110
- ],
111
- "environment": {
112
- "python": "3.10.12",
113
- "machine": "x86_64",
114
- "torch": "2.11.0+cu128",
115
- "transformers": "5.19.0.dev0",
116
- "tokenizers": "0.23.1"
117
- },
118
- "sha256": {
119
- "LICENSE": "43070e2d4e532684de521b885f385d0841030efa2b1a20bafb76133a5e1379c1",
120
- "config.json": "7a55bffa8e892b3f6cac45020c9f307f98563ba5ae3bb4cee7d92a775eb35a5f",
121
- "model.safetensors": "26bacd6b7e5e6ff3f9ffd3218544ef84ddbab096e4e4ba1c5849b0c7a476f184",
122
- "tokenizer.json": "ce64fce797c24f68df90b40a3f74f579b336a493db14bd583fd520ea0d8c9a98",
123
- "tokenizer_config.json": "a025160ef0431f1a392f6f050c1310f4c5d9fb6f275932dbccba73c4d214bf10",
124
- "vocab.txt": "07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3"
125
- }
126
  }
 
1
  {
2
+ "fixture": "hf-internal-testing/mic-bert-slim",
3
+ "key": "7ce74647df48e43332a1634bb3c9c123e2845de5a9401b574555e1964f417d11",
4
+ "key_fields": {
5
+ "architectures": [
6
+ "BertForMaskedLM"
7
+ ],
8
+ "output_hidden_states": false,
9
+ "return_dict": true,
10
+ "chunk_size_feed_forward": 0,
11
+ "is_encoder_decoder": false,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1"
15
+ },
16
+ "label2id": {
17
+ "LABEL_0": 0,
18
+ "LABEL_1": 1
19
+ },
20
+ "problem_type": null,
21
+ "vocab_size": 30522,
22
+ "hidden_size": 64,
23
+ "num_hidden_layers": 2,
24
+ "num_attention_heads": 4,
25
+ "intermediate_size": 128,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "attention_probs_dropout_prob": 0.1,
29
+ "max_position_embeddings": 512,
30
+ "type_vocab_size": 2,
31
+ "initializer_range": 0.02,
32
+ "layer_norm_eps": 1e-12,
33
+ "pad_token_id": 0,
34
+ "use_cache": true,
35
+ "classifier_dropout": null,
36
+ "is_decoder": false,
37
+ "add_cross_attention": false,
38
+ "bos_token_id": null,
39
+ "eos_token_id": null,
40
+ "tie_word_embeddings": true,
41
+ "gradient_checkpointing": false,
42
+ "model_type": "bert",
43
+ "position_embedding_type": "absolute",
44
+ "output_attentions": false
45
  },
46
+ "covers": {
47
+ "google-bert/bert-base-uncased": "86b5e0934494bd15c9632b12f734a8a67f723594"
 
48
  },
49
+ "built_from": {
50
+ "repo": "google-bert/bert-base-uncased",
51
+ "revision": "86b5e0934494bd15c9632b12f734a8a67f723594"
52
+ },
53
+ "seed": 17,
54
+ "dtype": "float32",
55
+ "builder": "example/build_fixtures.py",
56
+ "model_class": "BertForMaskedLM",
57
+ "parameters": 2088186,
58
+ "missing_parameters": [],
59
+ "checkpoint_inspection": "parameter metadata",
60
+ "captured": {
61
+ "call": "training step",
62
+ "inputs": [
63
+ "attention_mask",
64
+ "input_ids",
65
+ "labels",
66
+ "token_type_ids"
67
+ ]
68
+ },
69
+ "weights": "random",
70
+ "gate": {
71
+ "random": {
72
+ "pass": true,
73
+ "accepted_insensitive": {},
74
+ "threshold": 0.001,
75
+ "deltas": {
76
+ "input_ids:roll_batch": 0.720638632774353,
77
+ "input_ids:reverse": 0.7979322671890259,
78
+ "token_type_ids:all_ones": 0.7735698223114014,
79
+ "attention_mask:all_ones": 0.0027810335159301758
80
+ },
81
+ "weakest": "attention_mask:all_ones",
82
+ "no_perturbation_defined": []
83
+ }
84
+ },
85
+ "numeric_health": {
86
+ "float32": {
87
+ "outputs_finite": true,
88
+ "loss_finite": true,
89
+ "gradients_finite": true,
90
+ "finite": true
91
+ },
92
+ "bfloat16": {
93
+ "outputs_finite": true,
94
+ "loss_finite": true,
95
+ "gradients_finite": true,
96
+ "finite": true
97
+ },
98
+ "float16": {
99
+ "outputs_finite": true,
100
+ "loss_finite": true,
101
+ "gradients_finite": true,
102
+ "finite": true
103
+ }
104
+ },
105
+ "copied_unchanged": [
106
+ "LICENSE",
107
+ "tokenizer.json",
108
+ "tokenizer_config.json",
109
+ "vocab.txt"
110
+ ],
111
+ "environment": {
112
+ "python": "3.10.12",
113
+ "machine": "x86_64",
114
+ "torch": "2.11.0+cu128",
115
+ "transformers": "5.19.0.dev0",
116
+ "tokenizers": "0.23.1"
 
 
 
117
  },
118
+ "sha256": {
119
+ "LICENSE": "43070e2d4e532684de521b885f385d0841030efa2b1a20bafb76133a5e1379c1",
120
+ "config.json": "7a55bffa8e892b3f6cac45020c9f307f98563ba5ae3bb4cee7d92a775eb35a5f",
121
+ "model.safetensors": "66933decaaf67b913b25bbfccb7456403ba66acd452c4ee99bdc5404b5492ead",
122
+ "tokenizer.json": "ce64fce797c24f68df90b40a3f74f579b336a493db14bd583fd520ea0d8c9a98",
123
+ "tokenizer_config.json": "a025160ef0431f1a392f6f050c1310f4c5d9fb6f275932dbccba73c4d214bf10",
124
+ "vocab.txt": "07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3"
125
  },
126
+ "serialization": {
127
+ "file": "model.safetensors",
128
+ "reverted_conversions": [
129
+ "WeightRenaming: ['LayerNorm.gamma'] -> ['LayerNorm.weight']",
130
+ "WeightRenaming: ['LayerNorm.beta'] -> ['LayerNorm.bias']"
131
+ ],
132
+ "migrated_from": "model.safetensors"
133
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26bacd6b7e5e6ff3f9ffd3218544ef84ddbab096e4e4ba1c5849b0c7a476f184
3
- size 8357384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66933decaaf67b913b25bbfccb7456403ba66acd452c4ee99bdc5404b5492ead
3
+ size 8357376