PatrickSchwabl commited on
Commit
3b047b1
1 Parent(s): d464339

Upload 6 files

Browse files
Files changed (4) hide show
  1. config.json +4 -3
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +2 -2
  4. tokenizer_config.json +6 -0
config.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "_name_or_path": "./results/runs_fearspeech/checkpoint-320000",
3
  "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForMaskedLM"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
@@ -15,11 +15,12 @@
15
  "n_layers": 6,
16
  "output_past": true,
17
  "pad_token_id": 0,
 
18
  "qa_dropout": 0.1,
19
  "seq_classif_dropout": 0.2,
20
  "sinusoidal_pos_embds": true,
21
  "tie_weights_": true,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.30.2",
24
  "vocab_size": 31102
25
  }
 
1
  {
2
+ "_name_or_path": "/home/fear_speech_project/BERT_final_domain_adapted_model/",
3
  "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
 
15
  "n_layers": 6,
16
  "output_past": true,
17
  "pad_token_id": 0,
18
+ "problem_type": "single_label_classification",
19
  "qa_dropout": 0.1,
20
  "seq_classif_dropout": 0.2,
21
  "sinusoidal_pos_embds": true,
22
  "tie_weights_": true,
23
  "torch_dtype": "float32",
24
+ "transformers_version": "4.31.0",
25
  "vocab_size": 31102
26
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd9868ef027c467a1a188ca7ff6f0e2b89a51bad616eedf34ca3a9df1a7e003d
3
- size 269762097
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ccb0e661419e401a51a9336279ccb82a5ed5bc379f1845becd3c7103763ec4
3
+ size 269637293
tokenizer.json CHANGED
@@ -2,13 +2,13 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
- "Fixed": 512
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
9
  "padding": {
10
  "strategy": {
11
+ "Fixed": 128
12
  },
13
  "direction": "Right",
14
  "pad_to_multiple_of": null,
tokenizer_config.json CHANGED
@@ -5,13 +5,19 @@
5
  "mask_token": "[MASK]",
6
  "max_length": 512,
7
  "model_max_length": 512,
 
8
  "pad_token": "[PAD]",
 
9
  "padding": "max_length",
 
10
  "return_tensors": "pt",
11
  "sep_token": "[SEP]",
 
12
  "strip_accents": null,
13
  "tokenize_chinese_chars": true,
14
  "tokenizer_class": "DistilBertTokenizer",
15
  "truncation": false,
 
 
16
  "unk_token": "[UNK]"
17
  }
 
5
  "mask_token": "[MASK]",
6
  "max_length": 512,
7
  "model_max_length": 512,
8
+ "pad_to_multiple_of": null,
9
  "pad_token": "[PAD]",
10
+ "pad_token_type_id": 0,
11
  "padding": "max_length",
12
+ "padding_side": "right",
13
  "return_tensors": "pt",
14
  "sep_token": "[SEP]",
15
+ "stride": 0,
16
  "strip_accents": null,
17
  "tokenize_chinese_chars": true,
18
  "tokenizer_class": "DistilBertTokenizer",
19
  "truncation": false,
20
+ "truncation_side": "right",
21
+ "truncation_strategy": "longest_first",
22
  "unk_token": "[UNK]"
23
  }