neuer test
Browse files- README.md +2 -2
- config.json +15 -16
- pytorch_model.bin +2 -2
- special_tokens_map.json +5 -49
- tokenizer.json +0 -0
- tokenizer_config.json +12 -63
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: cc-by-4.0
|
3 |
-
base_model: deepset/
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# bert-finetuned-squad
|
15 |
|
16 |
-
This model is a fine-tuned version of [deepset/
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
1 |
---
|
2 |
license: cc-by-4.0
|
3 |
+
base_model: deepset/bert-large-uncased-whole-word-masking-squad2
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# bert-finetuned-squad
|
15 |
|
16 |
+
This model is a fine-tuned version of [deepset/bert-large-uncased-whole-word-masking-squad2](https://huggingface.co/deepset/bert-large-uncased-whole-word-masking-squad2) on the None dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
config.json
CHANGED
@@ -1,30 +1,29 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "deepset/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
-
"
|
10 |
-
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout_prob": 0.1,
|
13 |
-
"hidden_size":
|
14 |
"initializer_range": 0.02,
|
15 |
-
"intermediate_size":
|
16 |
"language": "english",
|
17 |
-
"layer_norm_eps": 1e-
|
18 |
-
"max_position_embeddings":
|
19 |
-
"model_type": "
|
20 |
-
"name": "
|
21 |
-
"num_attention_heads":
|
22 |
-
"num_hidden_layers":
|
23 |
-
"
|
|
|
24 |
"position_embedding_type": "absolute",
|
25 |
"torch_dtype": "float32",
|
26 |
"transformers_version": "4.33.3",
|
27 |
-
"type_vocab_size":
|
28 |
"use_cache": true,
|
29 |
-
"vocab_size":
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "deepset/bert-large-uncased-whole-word-masking-squad2",
|
3 |
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "squad2",
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
"language": "english",
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"name": "Bert",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
"position_embedding_type": "absolute",
|
24 |
"torch_dtype": "float32",
|
25 |
"transformers_version": "4.33.3",
|
26 |
+
"type_vocab_size": 2,
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 30522
|
29 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:607fad386e01ce76ae61a78a539c9c4cca18be5178e14f9f220dbd2e92cee67c
|
3 |
+
size 1336511145
|
special_tokens_map.json
CHANGED
@@ -1,51 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
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 |
-
}
|
51 |
}
|
|
|
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
@@ -1,66 +1,15 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": {
|
4 |
-
"__type": "AddedToken",
|
5 |
-
"content": "<s>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false
|
10 |
-
},
|
11 |
"clean_up_tokenization_spaces": true,
|
12 |
-
"cls_token":
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
"
|
21 |
-
"
|
22 |
-
|
23 |
-
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": true,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false
|
28 |
-
},
|
29 |
-
"errors": "replace",
|
30 |
-
"full_tokenizer_file": null,
|
31 |
-
"mask_token": {
|
32 |
-
"__type": "AddedToken",
|
33 |
-
"content": "<mask>",
|
34 |
-
"lstrip": true,
|
35 |
-
"normalized": true,
|
36 |
-
"rstrip": false,
|
37 |
-
"single_word": false
|
38 |
-
},
|
39 |
-
"model_max_length": 512,
|
40 |
-
"pad_token": {
|
41 |
-
"__type": "AddedToken",
|
42 |
-
"content": "<pad>",
|
43 |
-
"lstrip": false,
|
44 |
-
"normalized": true,
|
45 |
-
"rstrip": false,
|
46 |
-
"single_word": false
|
47 |
-
},
|
48 |
-
"sep_token": {
|
49 |
-
"__type": "AddedToken",
|
50 |
-
"content": "</s>",
|
51 |
-
"lstrip": false,
|
52 |
-
"normalized": true,
|
53 |
-
"rstrip": false,
|
54 |
-
"single_word": false
|
55 |
-
},
|
56 |
-
"tokenizer_class": "RobertaTokenizer",
|
57 |
-
"trim_offsets": true,
|
58 |
-
"unk_token": {
|
59 |
-
"__type": "AddedToken",
|
60 |
-
"content": "<unk>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": true,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false
|
65 |
-
}
|
66 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": true,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4027
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:578d709aec9c86edaf86585b23a4a9ba186efec1f46db575f2bafb612894dcd6
|
3 |
size 4027
|