mprzymus commited on
Commit
1a26892
1 Parent(s): a49a862

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +15 -22
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +4 -1
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,42 +1,35 @@
1
  {
2
- "_name_or_path": "bert-base-chinese",
 
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "directionality": "bidi",
9
- "hidden_act": "gelu",
10
- "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "id2label": {
13
  "0": "positive",
14
  "1": "neutral",
15
  "2": "negative"
16
  },
17
  "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
  "label2id": {
20
  "negative": 2,
21
  "neutral": 1,
22
  "positive": 0
23
  },
24
- "layer_norm_eps": 1e-12,
25
  "max_position_embeddings": 512,
26
- "model_type": "bert",
27
- "num_attention_heads": 12,
28
- "num_hidden_layers": 12,
29
  "pad_token_id": 0,
30
- "pooler_fc_size": 768,
31
- "pooler_num_attention_heads": 12,
32
- "pooler_num_fc_layers": 3,
33
- "pooler_size_per_head": 128,
34
- "pooler_type": "first_token_transform",
35
- "position_embedding_type": "absolute",
36
  "problem_type": "single_label_classification",
 
 
 
 
37
  "torch_dtype": "float32",
38
  "transformers_version": "4.30.2",
39
- "type_vocab_size": 2,
40
- "use_cache": true,
41
- "vocab_size": 21128
42
  }
 
1
  {
2
+ "_name_or_path": "sentence-transformers/distiluse-base-multilingual-cased-v1",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
 
 
11
  "id2label": {
12
  "0": "positive",
13
  "1": "neutral",
14
  "2": "negative"
15
  },
16
  "initializer_range": 0.02,
 
17
  "label2id": {
18
  "negative": 2,
19
  "neutral": 1,
20
  "positive": 0
21
  },
 
22
  "max_position_embeddings": 512,
23
+ "model_type": "distilbert",
24
+ "n_heads": 12,
25
+ "n_layers": 6,
26
  "pad_token_id": 0,
 
 
 
 
 
 
27
  "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.30.2",
34
+ "vocab_size": 119547
 
 
35
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:343d10fec860bd0038d4006ea8301383952a566f94154dea722509b77e4cb23f
3
- size 409152629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cff074f226930a72da81dc3f96067d733bc288f7257be9adc0e779b1d32cc43
3
+ size 541343405
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,16 @@
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
 
4
  "do_lower_case": false,
5
  "mask_token": "[MASK]",
 
6
  "model_max_length": 512,
 
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "strip_accents": null,
10
  "tokenize_chinese_chars": true,
11
- "tokenizer_class": "BertTokenizer",
12
  "unk_token": "[UNK]"
13
  }
 
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
  "do_lower_case": false,
6
  "mask_token": "[MASK]",
7
+ "max_len": 512,
8
  "model_max_length": 512,
9
+ "never_split": null,
10
  "pad_token": "[PAD]",
11
  "sep_token": "[SEP]",
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "DistilBertTokenizer",
15
  "unk_token": "[UNK]"
16
  }
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff