Hugging Face's logo

mHossain
/
bengali_pos_v1_kw

Token Classification
Transformers
TensorBoard
Safetensors
electra
Inference Endpoints
Model card Files Metrics Community
mHossain commited on
Commit
a3f79a4
•
1 Parent(s): 41930a5

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +119 -0
  2. model.safetensors +3 -0
  3. runs/Dec31_01-21-35_c4cf9a7a9e4f/events.out.tfevents.1703985697.c4cf9a7a9e4f.898.0 +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "csebuetnlp/banglabert_large",
3
+ "_num_labels": 2,
4
+ "amp": true,
5
+ "architectures": [
6
+ "ElectraForTokenClassification"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "embedding_size": 1024,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "ADD",
16
+ "1": "AFX",
17
+ "2": "CC",
18
+ "3": "CD",
19
+ "4": "DT",
20
+ "5": "EX",
21
+ "6": "FW",
22
+ "7": "HYPH",
23
+ "8": "IN",
24
+ "9": "JJ",
25
+ "10": "JJR",
26
+ "11": "JJS",
27
+ "12": "LS",
28
+ "13": "MD",
29
+ "14": "NFP",
30
+ "15": "NN",
31
+ "16": "NNP",
32
+ "17": "NNPS",
33
+ "18": "NNS",
34
+ "19": "PDT",
35
+ "20": "POS",
36
+ "21": "PRP",
37
+ "22": "PRP$",
38
+ "23": "RB",
39
+ "24": "RBR",
40
+ "25": "RBS",
41
+ "26": "RP",
42
+ "27": "SYM",
43
+ "28": "TO",
44
+ "29": "UH",
45
+ "30": "VB",
46
+ "31": "VBD",
47
+ "32": "VBG",
48
+ "33": "VBN",
49
+ "34": "VBP",
50
+ "35": "VBZ",
51
+ "36": "WDT",
52
+ "37": "WP",
53
+ "38": "WP$",
54
+ "39": "WRB",
55
+ "40": "XX"
56
+ },
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": 4096,
59
+ "label2id": {
60
+ "ADD": 0,
61
+ "AFX": 1,
62
+ "CC": 2,
63
+ "CD": 3,
64
+ "DT": 4,
65
+ "EX": 5,
66
+ "FW": 6,
67
+ "HYPH": 7,
68
+ "IN": 8,
69
+ "JJ": 9,
70
+ "JJR": 10,
71
+ "JJS": 11,
72
+ "LS": 12,
73
+ "MD": 13,
74
+ "NFP": 14,
75
+ "NN": 15,
76
+ "NNP": 16,
77
+ "NNPS": 17,
78
+ "NNS": 18,
79
+ "PDT": 19,
80
+ "POS": 20,
81
+ "PRP": 21,
82
+ "PRP$": 22,
83
+ "RB": 23,
84
+ "RBR": 24,
85
+ "RBS": 25,
86
+ "RP": 26,
87
+ "SYM": 27,
88
+ "TO": 28,
89
+ "UH": 29,
90
+ "VB": 30,
91
+ "VBD": 31,
92
+ "VBG": 32,
93
+ "VBN": 33,
94
+ "VBP": 34,
95
+ "VBZ": 35,
96
+ "WDT": 36,
97
+ "WP": 37,
98
+ "WP$": 38,
99
+ "WRB": 39,
100
+ "XX": 40
101
+ },
102
+ "layer_norm_eps": 1e-12,
103
+ "max_position_embeddings": 512,
104
+ "model_type": "electra",
105
+ "num_attention_heads": 16,
106
+ "num_hidden_layers": 24,
107
+ "output_past": true,
108
+ "pad_token_id": 0,
109
+ "position_embedding_type": "absolute",
110
+ "summary_activation": "gelu",
111
+ "summary_last_dropout": 0.1,
112
+ "summary_type": "first",
113
+ "summary_use_proj": true,
114
+ "torch_dtype": "float32",
115
+ "transformers_version": "4.35.2",
116
+ "type_vocab_size": 2,
117
+ "use_cache": true,
118
+ "vocab_size": 32000
119
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4adc8c6dc093d33834fb47f778fafad96e06e0d25ff47c50e88dcf82be4bddc5
3
+ size 1342639116
runs/Dec31_01-21-35_c4cf9a7a9e4f/events.out.tfevents.1703985697.c4cf9a7a9e4f.898.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60321239e1afbeb33f8d89ef2083d4ce93e9262e40afad9455779ee3684c9b63
3
+ size 12508
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "full_tokenizer_file": null,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": false,
56
+ "tokenizer_class": "ElectraTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86d9f978e222879015815b58da090cd588cfcd4bf442fbfabb4707f7714827c
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff