MauroExtrac commited on
Commit
d4dc56f
·
verified ·
1 Parent(s): db38789

Training in progress epoch 0

Browse files
Files changed (5) hide show
  1. config.json +22 -23
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +1 -1
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,18 +1,17 @@
1
  {
2
- "_name_or_path": "bert-base-cased",
 
3
  "architectures": [
4
- "BertForTokenClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "id2label": {
13
- "0": "O",
14
- "1": "B-PER",
15
- "2": "I-PER",
16
  "3": "B-ORG",
17
  "4": "I-ORG",
18
  "5": "B-LOC",
@@ -21,28 +20,28 @@
21
  "8": "I-MISC"
22
  },
23
  "initializer_range": 0.02,
24
- "intermediate_size": 3072,
25
  "label2id": {
26
  "B-LOC": 5,
27
  "B-MISC": 7,
28
  "B-ORG": 3,
29
- "B-PER": 1,
30
  "I-LOC": 6,
31
  "I-MISC": 8,
32
  "I-ORG": 4,
33
- "I-PER": 2,
34
- "O": 0
35
  },
36
- "layer_norm_eps": 1e-12,
37
  "max_position_embeddings": 512,
38
- "model_type": "bert",
39
- "num_attention_heads": 12,
40
- "num_hidden_layers": 12,
 
41
  "pad_token_id": 0,
42
- "position_embedding_type": "absolute",
 
 
 
43
  "torch_dtype": "float32",
44
  "transformers_version": "4.46.3",
45
- "type_vocab_size": 2,
46
- "use_cache": true,
47
- "vocab_size": 28996
48
  }
 
1
  {
2
+ "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForTokenClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "id2label": {
12
+ "0": "OUT",
13
+ "1": "B-PERS",
14
+ "2": "I-PERS",
15
  "3": "B-ORG",
16
  "4": "I-ORG",
17
  "5": "B-LOC",
 
20
  "8": "I-MISC"
21
  },
22
  "initializer_range": 0.02,
 
23
  "label2id": {
24
  "B-LOC": 5,
25
  "B-MISC": 7,
26
  "B-ORG": 3,
27
+ "B-PERS": 1,
28
  "I-LOC": 6,
29
  "I-MISC": 8,
30
  "I-ORG": 4,
31
+ "I-PERS": 2,
32
+ "OUT": 0
33
  },
 
34
  "max_position_embeddings": 512,
35
+ "model_type": "distilbert",
36
+ "n_heads": 12,
37
+ "n_layers": 6,
38
+ "output_past": true,
39
  "pad_token_id": 0,
40
+ "qa_dropout": 0.1,
41
+ "seq_classif_dropout": 0.2,
42
+ "sinusoidal_pos_embds": false,
43
+ "tie_weights_": true,
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.46.3",
46
+ "vocab_size": 119547
 
 
47
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc2f9dffeab484b72400bd22fd0211f657f506945d0fb376d16e0693125b5aa
3
- size 430929740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd7f0ca1b0e2277cef08988ac465bc3721ed39e3a7af75f17cc36ec9dba968fd
3
+ size 538976356
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -50,6 +50,6 @@
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
- "tokenizer_class": "BertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
 
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
52
  "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
  "unk_token": "[UNK]"
55
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff