Hugging Face's logo

huggingface-mic
/
mpnet-base-mic

Safetensors
mpnet
mic
test-artifact
Model card Files
xet
 Community
mpnet-base-mic
File size: 3,068 Bytes
9d98c3d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
{
 "fixture": "huggingface-mic/mpnet-base-mic",
 "key": "f651cf653329690ffdac8316da0dfe3bedf2a7d22cbcfb81644af500233f2eaa",
 "key_fields": {
  "architectures": [
   "MPNetForMaskedLM"
  ],
  "output_hidden_states": false,
  "return_dict": true,
  "chunk_size_feed_forward": 0,
  "is_encoder_decoder": false,
  "id2label": {
   "0": "LABEL_0",
   "1": "LABEL_1"
  },
  "label2id": {
   "LABEL_0": 0,
   "LABEL_1": 1
  },
  "problem_type": null,
  "vocab_size": 30527,
  "hidden_size": 64,
  "num_hidden_layers": 2,
  "num_attention_heads": 4,
  "intermediate_size": 128,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "max_position_embeddings": 514,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-05,
  "relative_attention_num_buckets": 32,
  "pad_token_id": 1,
  "bos_token_id": 0,
  "eos_token_id": 2,
  "tie_word_embeddings": true,
  "model_type": "mpnet",
  "output_attentions": false
 },
 "covers": {
  "microsoft/mpnet-base": "6996ce1e91bd2a9c7d7f61daec37463394f73f09"
 },
 "built_from": {
  "repo": "microsoft/mpnet-base",
  "revision": "6996ce1e91bd2a9c7d7f61daec37463394f73f09"
 },
 "seed": 17,
 "dtype": "float32",
 "builder": "example/build_fixtures.py",
 "model_class": "MPNetForMaskedLM",
 "parameters": 2088639,
 "missing_parameters": [],
 "checkpoint_inspection": "parameter headers/indexes; bounded binary fallback",
 "numeric_health_scope": "CPU float32/bfloat16/float16; autocast for low-precision losses",
 "captured": {
  "call": "training step",
  "inputs": [
   "attention_mask",
   "input_ids",
   "labels"
  ],
  "class": "MPNetForMaskedLM"
 },
 "weights": "random",
 "gate": {
  "random": {
   "pass": true,
   "accepted_insensitive": {},
   "threshold": 0.001,
   "deltas": {
    "input_ids:roll_batch": 0.9448294639587402,
    "input_ids:reverse": 1.0667192935943604,
    "attention_mask:all_ones": 0.003877967596054077
   },
   "weakest": "attention_mask:all_ones",
   "no_perturbation_defined": []
  }
 },
 "numeric_health": {
  "float32": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  },
  "bfloat16": {
   "outputs_finite": true,
   "loss_finite": true,
   "gradients_finite": true,
   "finite": true
  },
  "float16": {
   "outputs_finite": true,
   "loss_finite": true,
   "unscaled_gradients_finite": true,
   "finite": true
  }
 },
 "copied_unchanged": [
  "tokenizer.json",
  "tokenizer_config.json",
  "vocab.txt"
 ],
 "environment": {
  "python": "3.12.12",
  "machine": "arm64",
  "torch": "2.14.1",
  "transformers": "5.22.0.dev0",
  "tokenizers": "0.23.3"
 },
 "sha256": {
  "config.json": "fb3dc6d23ef3e0cb7732f21600a1fabaff080945c5ea5af84ca7160970c1eaec",
  "model.safetensors": "dd73d8ca71d581e211b9d528ccd10d65c1554f232123ceb930809e255d0f4d7f",
  "tokenizer.json": "47ccb942058221e560ce5a5cfa2969d54d3b8422eb0f6d01d098b1aa81741bdb",
  "tokenizer_config.json": "5ab9097b4149371c5fd52b2d6e26cb6f9c07c0d19fcfdda895b1adad6b57c3e0",
  "vocab.txt": "dbd90cb94e2247bd4d4ccaecbf616d2290e66691d7d5e5bb81f063c2d0649ada"
 }
}