Hugging Face's logo

mh01
/
silver-retriever-base-v1.1_ner

Text Classification
Transformers
TensorBoard
Safetensors
bert
Inference Endpoints
Model card Files Metrics Community
mh01 commited on
Commit
7532096
·
verified ·
1 Parent(s): 69785a5

Training in progress, epoch 2

Browse files
Files changed (9) hide show
  1. config.json +43 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Jul19_23-35-34_ca43a1618e63/events.out.tfevents.1721432135.ca43a1618e63.224.3 +3 -0
  5. special_tokens_map.json +44 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +64 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ipipan/silver-retriever-base-v1.1",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "noEntity",
13
+ "1": "placeName",
14
+ "2": "persName",
15
+ "3": "orgName",
16
+ "4": "time",
17
+ "5": "geogName"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "geogName": 5,
23
+ "noEntity": 0,
24
+ "orgName": 3,
25
+ "persName": 2,
26
+ "placeName": 1,
27
+ "time": 4
28
+ },
29
+ "layer_norm_eps": 1e-12,
30
+ "max_position_embeddings": 514,
31
+ "model_type": "bert",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "tokenizer_class": "HerbertTokenizerFast",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.42.4",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 50000
43
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f73d0208efbf0c55dc89385cc75bbf1f5e7aef1f3aed78be59e8d58ce9dddd
3
+ size 497813520
runs/Jul19_23-35-34_ca43a1618e63/events.out.tfevents.1721432135.ca43a1618e63.224.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c3b15ad8fc1e6256a507c27cf0c9269939172646286ac4276a446660159981
3
+ size 7312
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<unk>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
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": "<unk>",
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
+ "additional_special_tokens": [],
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "do_lowercase_and_remove_accent": false,
49
+ "id2lang": null,
50
+ "lang2id": null,
51
+ "mask_token": "<mask>",
52
+ "max_length": 512,
53
+ "model_max_length": 512,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "<pad>",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "</s>",
59
+ "stride": 0,
60
+ "tokenizer_class": "HerbertTokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "<unk>"
64
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e1f6d2740caf04fa1e5818168bbac5f519d1a51e8c758d50b916755f2615046
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff