Hugging Face's logo

raulgdp
/
BETO-conll2002-ner

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
Community
raulgdp commited on
Commit
ece3b8b
·
verified ·
1 Parent(s): 1aec944

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. config.json +64 -0
  2. labels.json +11 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +19 -0
  5. spiece.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +94 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLNetForTokenClassification"
4
+ ],
5
+ "attn_type": "bi",
6
+ "bi_data": false,
7
+ "bos_token_id": 1,
8
+ "clamp_len": -1,
9
+ "d_head": 64,
10
+ "d_inner": 4096,
11
+ "d_model": 1024,
12
+ "dropout": 0.1,
13
+ "dtype": "float32",
14
+ "end_n_top": 5,
15
+ "eos_token_id": 2,
16
+ "ff_activation": "gelu",
17
+ "id2label": {
18
+ "0": "B-LOC",
19
+ "1": "B-MISC",
20
+ "2": "B-ORG",
21
+ "3": "B-PER",
22
+ "4": "I-LOC",
23
+ "5": "I-MISC",
24
+ "6": "I-ORG",
25
+ "7": "I-PER",
26
+ "8": "O"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "label2id": {
30
+ "B-LOC": 0,
31
+ "B-MISC": 1,
32
+ "B-ORG": 2,
33
+ "B-PER": 3,
34
+ "I-LOC": 4,
35
+ "I-MISC": 5,
36
+ "I-ORG": 6,
37
+ "I-PER": 7,
38
+ "O": 8
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "mem_len": null,
42
+ "model_type": "xlnet",
43
+ "n_head": 16,
44
+ "n_layer": 24,
45
+ "pad_token_id": 5,
46
+ "reuse_len": null,
47
+ "same_length": false,
48
+ "start_n_top": 5,
49
+ "summary_activation": "tanh",
50
+ "summary_last_dropout": 0.1,
51
+ "summary_type": "last",
52
+ "summary_use_proj": true,
53
+ "task_specific_params": {
54
+ "text-generation": {
55
+ "do_sample": true,
56
+ "max_length": 250
57
+ }
58
+ },
59
+ "transformers_version": "4.57.1",
60
+ "untie_r": true,
61
+ "use_mems_eval": true,
62
+ "use_mems_train": false,
63
+ "vocab_size": 32000
64
+ }
labels.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ "B-LOC",
3
+ "B-MISC",
4
+ "B-ORG",
5
+ "B-PER",
6
+ "I-LOC",
7
+ "I-MISC",
8
+ "I-ORG",
9
+ "I-PER",
10
+ "O"
11
+ ]
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0e0bfa19129b2848972ec3788a1133f2777ead21fe06490d98dc7c06ff8961
3
+ size 1441157604
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<eop>",
4
+ "<eod>"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<cls>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "<sep>",
18
+ "unk_token": "<unk>"
19
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8c1c0bc2854d1af911a8550288c1258af5ba50277f3a5c829b98eb86fc5646
3
+ size 798011
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<cls>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<sep>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<eod>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<eop>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "additional_special_tokens": [
77
+ "<eop>",
78
+ "<eod>"
79
+ ],
80
+ "bos_token": "<s>",
81
+ "clean_up_tokenization_spaces": false,
82
+ "cls_token": "<cls>",
83
+ "do_lower_case": false,
84
+ "eos_token": "</s>",
85
+ "extra_special_tokens": {},
86
+ "keep_accents": false,
87
+ "mask_token": "<mask>",
88
+ "model_max_length": 1000000000000000019884624838656,
89
+ "pad_token": "<pad>",
90
+ "remove_space": true,
91
+ "sep_token": "<sep>",
92
+ "tokenizer_class": "XLNetTokenizer",
93
+ "unk_token": "<unk>"
94
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9b6f847c95ada2e69be3282857a722a779bf5452435e8f6abd284ac9b98a2b
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff