mprzymus commited on
Commit
b168577
·
1 Parent(s): 814f3ad

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "_name_or_path": "allegro/herbert-base-cased",
 
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": "optimism",
13
  "1": "anger",
@@ -15,25 +15,23 @@
15
  "3": "sadness"
16
  },
17
  "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
  "label2id": {
20
  "anger": 1,
21
  "joy": 2,
22
  "optimism": 0,
23
  "sadness": 3
24
  },
25
- "layer_norm_eps": 1e-12,
26
- "max_position_embeddings": 514,
27
- "model_type": "bert",
28
- "num_attention_heads": 12,
29
- "num_hidden_layers": 12,
30
- "pad_token_id": 1,
31
- "position_embedding_type": "absolute",
32
  "problem_type": "single_label_classification",
33
- "tokenizer_class": "HerbertTokenizerFast",
 
 
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.30.2",
36
- "type_vocab_size": 2,
37
- "use_cache": true,
38
- "vocab_size": 50000
39
  }
 
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": "optimism",
13
  "1": "anger",
 
15
  "3": "sadness"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "anger": 1,
20
  "joy": 2,
21
  "optimism": 0,
22
  "sadness": 3
23
  },
24
+ "max_position_embeddings": 512,
25
+ "model_type": "distilbert",
26
+ "n_heads": 12,
27
+ "n_layers": 6,
28
+ "pad_token_id": 0,
 
 
29
  "problem_type": "single_label_classification",
30
+ "qa_dropout": 0.1,
31
+ "seq_classif_dropout": 0.2,
32
+ "sinusoidal_pos_embds": false,
33
+ "tie_weights_": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.30.2",
36
+ "vocab_size": 119547
 
 
37
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e091b954db5d3da1a259fa39a6e3b52b198b320020d9ebe859a6b5ba8d251d44
3
- size 497856629
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e89e666006d22b690f4471fa8b34a6a9c7bd1628fd2cdb53c454fc0e901a672
3
+ size 541346477
special_tokens_map.json CHANGED
@@ -1,8 +1,7 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "mask_token": "<mask>",
5
- "pad_token": "<pad>",
6
- "sep_token": "</s>",
7
- "unk_token": "<unk>"
8
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,16 @@
1
  {
2
- "additional_special_tokens": [],
3
- "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
- "cls_token": "<s>",
6
- "do_lowercase_and_remove_accent": false,
7
- "id2lang": null,
8
- "lang2id": null,
9
- "mask_token": "<mask>",
10
  "model_max_length": 512,
11
- "pad_token": "<pad>",
12
- "sep_token": "</s>",
13
- "tokenizer_class": "HerbertTokenizer",
14
- "unk_token": "<unk>"
 
 
 
15
  }
 
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 ADDED
The diff for this file is too large to render. See raw diff