isakbos commited on
Commit
c17ceec
1 Parent(s): b83bafa

Updated model

Browse files
Files changed (4) hide show
  1. config.json +69 -10
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -1
config.json CHANGED
@@ -1,28 +1,87 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
  "QuantizedBertForSequenceClassification"
5
  ],
 
 
 
 
 
 
 
6
  "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "finetuning_task": "cola",
9
- "gradient_checkpointing": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
 
 
 
 
13
  "initializer_range": 0.02,
14
  "intermediate_size": 3072,
 
 
 
 
 
15
  "layer_norm_eps": 1e-12,
 
 
16
  "max_position_embeddings": 512,
17
  "model_type": "bert",
18
  "num_attention_heads": 12,
 
19
  "num_hidden_layers": 12,
 
 
 
 
 
20
  "pad_token_id": 0,
21
- "position_embedding_type": "absolute",
22
- "problem_type": "single_label_classification",
23
- "torch_dtype": "float32",
24
- "transformers_version": "4.12.5",
 
 
 
 
 
 
 
 
 
 
 
 
25
  "type_vocab_size": 2,
26
- "use_cache": true,
27
- "vocab_size": 30522
 
 
 
28
  }
 
1
  {
 
2
  "architectures": [
3
  "QuantizedBertForSequenceClassification"
4
  ],
5
+ "attention_key": {
6
+ "mode": "ema"
7
+ },
8
+ "attention_output": {
9
+ "mode": "ema",
10
+ "requantize_output": false
11
+ },
12
  "attention_probs_dropout_prob": 0.1,
13
+ "attention_query": {
14
+ "mode": "ema"
15
+ },
16
+ "attention_value": {
17
+ "mode": "ema",
18
+ "requantize_output": false
19
+ },
20
+ "bos_token_id": 0,
21
+ "do_sample": false,
22
+ "eos_token_ids": 0,
23
+ "ffn_intermediate": {
24
+ "mode": "ema",
25
+ "requantize_output": false
26
+ },
27
+ "ffn_output": {
28
+ "mode": "ema",
29
+ "requantize_output": false
30
+ },
31
+ "finetuning_task": null,
32
+ "head": {
33
+ "mode": "ema",
34
+ "requantize_output": false,
35
+ "start_step": 200
36
+ },
37
  "hidden_act": "gelu",
38
  "hidden_dropout_prob": 0.1,
39
  "hidden_size": 768,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
  "initializer_range": 0.02,
45
  "intermediate_size": 3072,
46
+ "is_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
  "layer_norm_eps": 1e-12,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
  "max_position_embeddings": 512,
55
  "model_type": "bert",
56
  "num_attention_heads": 12,
57
+ "num_beams": 1,
58
  "num_hidden_layers": 12,
59
+ "num_labels": 2,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_past": true,
64
  "pad_token_id": 0,
65
+ "pooler": {
66
+ "mode": "ema",
67
+ "requantize_output": false
68
+ },
69
+ "position_embeddings": {
70
+ "mode": "ema"
71
+ },
72
+ "pruned_heads": {},
73
+ "repetition_penalty": 1.0,
74
+ "temperature": 1.0,
75
+ "token_type_embeddings": {
76
+ "mode": "none"
77
+ },
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torchscript": false,
81
  "type_vocab_size": 2,
82
+ "use_bfloat16": false,
83
+ "vocab_size": 30522,
84
+ "word_embeddings": {
85
+ "mode": "ema"
86
+ }
87
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3384be928331ccffbc5eeb5ebdac69d039d9332fc032b24b4fed542161e55184
3
- size 438723541
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10008e2fb48f29e9880e55273e47516e41e75548b8ff6ef8ba40602b0118ca99
3
+ size 110019389
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
 
1
+ {"do_lower_case": true, "max_len": 512}