Hugging Face's logo

nes470
/
test-demo-qa

Question Answering
Transformers
Safetensors
roberta
Model card Files Community
nes470 commited on
Commit
3e70e21
路
verified 路
1 Parent(s): f97ad06

Upload DemoQAPipeline

Browse files
Files changed (7) hide show
  1. config.json +23 -17
  2. merges.txt +0 -0
  3. model.safetensors +2 -2
  4. special_tokens_map.json +25 -11
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +28 -24
  7. vocab.json +0 -0
config.json CHANGED
@@ -1,10 +1,11 @@
1
  {
2
- "_name_or_path": "datarpit/distilbert-base-uncased-finetuned-natural-questions",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForQuestionAnswering"
6
  ],
7
- "attention_dropout": 0.1,
 
 
8
  "custom_pipelines": {
9
  "demo-qa": {
10
  "impl": "__main__.DemoQAPipeline",
@@ -16,20 +17,25 @@
16
  ]
17
  }
18
  },
19
- "dim": 768,
20
- "dropout": 0.1,
21
- "hidden_dim": 3072,
 
 
22
  "initializer_range": 0.02,
23
- "max_position_embeddings": 512,
24
- "model_type": "distilbert",
25
- "n_heads": 12,
26
- "n_layers": 6,
27
- "pad_token_id": 0,
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": "4.40.1",
34
- "vocab_size": 30522
 
 
35
  }
 
1
  {
2
+ "_name_or_path": "deepset/roberta-base-squad2",
 
3
  "architectures": [
4
+ "RobertaForQuestionAnswering"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
  "custom_pipelines": {
10
  "demo-qa": {
11
  "impl": "__main__.DemoQAPipeline",
 
17
  ]
18
  }
19
  },
20
+ "eos_token_id": 2,
21
+ "gradient_checkpointing": false,
22
+ "hidden_act": "gelu",
23
+ "hidden_dropout_prob": 0.1,
24
+ "hidden_size": 768,
25
  "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "language": "english",
28
+ "layer_norm_eps": 1e-05,
29
+ "max_position_embeddings": 514,
30
+ "model_type": "roberta",
31
+ "name": "Roberta",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 1,
35
+ "position_embedding_type": "absolute",
36
  "torch_dtype": "float32",
37
  "transformers_version": "4.40.1",
38
+ "type_vocab_size": 1,
39
+ "use_cache": true,
40
+ "vocab_size": 50265
41
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90407c60361d11e97bce26a71582514196e980c2013e883e34f36f18e2ec44c3
3
- size 265470032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea7c01c6ac8f7891ad23102e1569c5b414e8d74cbf8d8a587c3c90510c9cc166
3
+ size 496250232
special_tokens_map.json CHANGED
@@ -1,36 +1,50 @@
1
  {
 
 
 
 
 
 
 
2
  "cls_token": {
3
- "content": "[CLS]",
4
  "lstrip": false,
5
- "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
- "mask_token": {
10
- "content": "[MASK]",
11
  "lstrip": false,
12
- "normalized": false,
 
 
 
 
 
 
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "[PAD]",
18
  "lstrip": false,
19
- "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  },
23
  "sep_token": {
24
- "content": "[SEP]",
25
  "lstrip": false,
26
- "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "unk_token": {
31
- "content": "[UNK]",
32
  "lstrip": false,
33
- "normalized": false,
34
  "rstrip": false,
35
  "single_word": false
36
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
  "cls_token": {
10
+ "content": "<s>",
11
  "lstrip": false,
12
+ "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "eos_token": {
17
+ "content": "</s>",
18
  "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  },
30
  "pad_token": {
31
+ "content": "<pad>",
32
  "lstrip": false,
33
+ "normalized": true,
34
  "rstrip": false,
35
  "single_word": false
36
  },
37
  "sep_token": {
38
+ "content": "</s>",
39
  "lstrip": false,
40
+ "normalized": true,
41
  "rstrip": false,
42
  "single_word": false
43
  },
44
  "unk_token": {
45
+ "content": "<unk>",
46
  "lstrip": false,
47
+ "normalized": true,
48
  "rstrip": false,
49
  "single_word": false
50
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,55 +1,59 @@
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
- "100": {
12
- "content": "[UNK]",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "101": {
20
- "content": "[CLS]",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "102": {
28
- "content": "[SEP]",
29
  "lstrip": false,
30
- "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "103": {
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_lower_case": true,
47
- "mask_token": "[MASK]",
 
 
 
48
  "model_max_length": 512,
49
- "pad_token": "[PAD]",
50
- "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
- "unk_token": "[UNK]"
55
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
+ "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "do_lower_case": false,
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "full_tokenizer_file": null,
52
+ "mask_token": "<mask>",
53
  "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
 
59
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff