Zarcend commited on
Commit
dbec340
1 Parent(s): e027f36

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/tapas-large-finetuned-sqa",
3
+ "aggregation_labels": null,
4
+ "aggregation_loss_weight": 1.0,
5
+ "aggregation_temperature": 1.0,
6
+ "allow_empty_column_selection": false,
7
+ "answer_loss_cutoff": null,
8
+ "answer_loss_importance": 1.0,
9
+ "architectures": [
10
+ "TapasForQuestionAnswering"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "average_approximation_function": "ratio",
14
+ "average_logits_per_cell": false,
15
+ "cell_selection_preference": null,
16
+ "disable_per_token_loss": false,
17
+ "gradient_checkpointing": false,
18
+ "hidden_act": "gelu",
19
+ "hidden_dropout_prob": 0.1,
20
+ "hidden_size": 1024,
21
+ "huber_loss_delta": null,
22
+ "init_cell_selection_weights_to_zero": false,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 4096,
25
+ "layer_norm_eps": 1e-12,
26
+ "max_num_columns": 32,
27
+ "max_num_rows": 64,
28
+ "max_position_embeddings": 1024,
29
+ "model_type": "tapas",
30
+ "no_aggregation_label_index": null,
31
+ "num_aggregation_labels": 0,
32
+ "num_attention_heads": 16,
33
+ "num_hidden_layers": 24,
34
+ "pad_token_id": 0,
35
+ "positive_label_weight": 10.0,
36
+ "reset_position_index_per_cell": true,
37
+ "select_one_column": true,
38
+ "softmax_temperature": 1.0,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.39.1",
41
+ "type_vocab_size": [
42
+ 3,
43
+ 256,
44
+ 256,
45
+ 2,
46
+ 256,
47
+ 256,
48
+ 10
49
+ ],
50
+ "type_vocab_sizes": [
51
+ 3,
52
+ 256,
53
+ 256,
54
+ 2,
55
+ 256,
56
+ 256,
57
+ 10
58
+ ],
59
+ "use_answer_as_supervision": null,
60
+ "use_gumbel_for_aggregation": false,
61
+ "use_gumbel_for_cells": false,
62
+ "use_normalized_answer_loss": false,
63
+ "vocab_size": 30522
64
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f10f62349b0df7e5e2c5c2559f6bc1ea54dffc83c535735f2f06897b216e5a7
3
+ size 1346968688
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[EMPTY]"
4
+ ],
5
+ "cls_token": "[CLS]",
6
+ "mask_token": "[MASK]",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "unk_token": "[UNK]"
10
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[EMPTY]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "100": {
20
+ "content": "[UNK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "101": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "102": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "103": {
44
+ "content": "[MASK]",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ }
51
+ },
52
+ "additional_special_tokens": [
53
+ "[EMPTY]"
54
+ ],
55
+ "cell_trim_length": -1,
56
+ "clean_up_tokenization_spaces": true,
57
+ "cls_token": "[CLS]",
58
+ "do_basic_tokenize": true,
59
+ "do_lower_case": true,
60
+ "drop_rows_to_fit": false,
61
+ "empty_token": "[EMPTY]",
62
+ "mask_token": "[MASK]",
63
+ "max_column_id": 512,
64
+ "max_question_length": null,
65
+ "max_row_id": 512,
66
+ "min_question_length": null,
67
+ "model_max_length": 512,
68
+ "never_split": null,
69
+ "pad_token": "[PAD]",
70
+ "sep_token": "[SEP]",
71
+ "strip_accents": null,
72
+ "strip_column_names": false,
73
+ "tokenize_chinese_chars": true,
74
+ "tokenizer_class": "TapasTokenizer",
75
+ "unk_token": "[UNK]",
76
+ "update_answer_coordinates": false
77
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff