First irst commit
Browse files- config.json +63 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"aggregation_labels": null,
|
3 |
+
"aggregation_loss_weight": 1.0,
|
4 |
+
"aggregation_temperature": 1.0,
|
5 |
+
"allow_empty_column_selection": false,
|
6 |
+
"answer_loss_cutoff": null,
|
7 |
+
"answer_loss_importance": 1.0,
|
8 |
+
"architectures": [
|
9 |
+
"TapasForMaskedLM"
|
10 |
+
],
|
11 |
+
"attention_probs_dropout_prob": 0.1,
|
12 |
+
"average_approximation_function": "ratio",
|
13 |
+
"average_logits_per_cell": false,
|
14 |
+
"cell_selection_preference": null,
|
15 |
+
"disable_per_token_loss": false,
|
16 |
+
"gradient_checkpointing": false,
|
17 |
+
"hidden_act": "gelu",
|
18 |
+
"hidden_dropout_prob": 0.1,
|
19 |
+
"hidden_size": 1024,
|
20 |
+
"huber_loss_delta": null,
|
21 |
+
"init_cell_selection_weights_to_zero": false,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 4096,
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_num_columns": 32,
|
26 |
+
"max_num_rows": 64,
|
27 |
+
"max_position_embeddings": 1024,
|
28 |
+
"model_type": "tapas",
|
29 |
+
"no_aggregation_label_index": null,
|
30 |
+
"num_aggregation_labels": 0,
|
31 |
+
"num_attention_heads": 16,
|
32 |
+
"num_hidden_layers": 24,
|
33 |
+
"pad_token_id": 0,
|
34 |
+
"positive_label_weight": 10.0,
|
35 |
+
"reset_position_index_per_cell": true,
|
36 |
+
"select_one_column": true,
|
37 |
+
"softmax_temperature": 1.0,
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.11.0.dev0",
|
40 |
+
"type_vocab_size": [
|
41 |
+
3,
|
42 |
+
256,
|
43 |
+
256,
|
44 |
+
2,
|
45 |
+
256,
|
46 |
+
256,
|
47 |
+
10
|
48 |
+
],
|
49 |
+
"type_vocab_sizes": [
|
50 |
+
3,
|
51 |
+
256,
|
52 |
+
256,
|
53 |
+
2,
|
54 |
+
256,
|
55 |
+
256,
|
56 |
+
10
|
57 |
+
],
|
58 |
+
"use_answer_as_supervision": null,
|
59 |
+
"use_gumbel_for_aggregation": false,
|
60 |
+
"use_gumbel_for_cells": false,
|
61 |
+
"use_normalized_answer_loss": false,
|
62 |
+
"vocab_size": 30522
|
63 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a992fa6081ab1a8116dc19603c0497569d06e411554b12ed9096811902379c58
|
3 |
+
size 1347198049
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[EMPTY]"]}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "empty_token": "[EMPTY]", "tokenize_chinese_chars": true, "strip_accents": null, "cell_trim_length": -1, "max_column_id": null, "max_row_id": null, "strip_column_names": false, "update_answer_coordinates": false, "min_question_length": null, "max_question_length": null, "model_max_length": 512, "additional_special_tokens": ["[EMPTY]"], "tokenizer_class": "TapasTokenizer"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|