Upload TFTapasForQuestionAnswering
Browse files- README.md +47 -0
- config.json +69 -0
- tf_model.h5 +3 -0
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_keras_callback
|
5 |
+
model-index:
|
6 |
+
- name: my-awesome-model
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
11 |
+
probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# my-awesome-model
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [google/tapas-base-finetuned-wtq](https://huggingface.co/google/tapas-base-finetuned-wtq) on an unknown dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- optimizer: None
|
37 |
+
- training_precision: float32
|
38 |
+
|
39 |
+
### Training results
|
40 |
+
|
41 |
+
|
42 |
+
|
43 |
+
### Framework versions
|
44 |
+
|
45 |
+
- Transformers 4.25.1
|
46 |
+
- TensorFlow 2.9.2
|
47 |
+
- Tokenizers 0.13.2
|
config.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/tapas-base-finetuned-wtq",
|
3 |
+
"aggregation_labels": {
|
4 |
+
"0": "NONE",
|
5 |
+
"1": "SUM",
|
6 |
+
"2": "AVERAGE",
|
7 |
+
"3": "COUNT"
|
8 |
+
},
|
9 |
+
"aggregation_loss_weight": 1.0,
|
10 |
+
"aggregation_temperature": 1.0,
|
11 |
+
"allow_empty_column_selection": false,
|
12 |
+
"answer_loss_cutoff": 0.664694,
|
13 |
+
"answer_loss_importance": 1.0,
|
14 |
+
"architectures": [
|
15 |
+
"TapasForQuestionAnswering"
|
16 |
+
],
|
17 |
+
"attention_probs_dropout_prob": 0.1,
|
18 |
+
"average_approximation_function": "ratio",
|
19 |
+
"average_logits_per_cell": false,
|
20 |
+
"cell_selection_preference": 0.207951,
|
21 |
+
"disable_per_token_loss": false,
|
22 |
+
"gradient_checkpointing": false,
|
23 |
+
"hidden_act": "gelu",
|
24 |
+
"hidden_dropout_prob": 0.1,
|
25 |
+
"hidden_size": 768,
|
26 |
+
"huber_loss_delta": 0.121194,
|
27 |
+
"init_cell_selection_weights_to_zero": true,
|
28 |
+
"initializer_range": 0.02,
|
29 |
+
"intermediate_size": 3072,
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"max_num_columns": 32,
|
32 |
+
"max_num_rows": 64,
|
33 |
+
"max_position_embeddings": 1024,
|
34 |
+
"model_type": "tapas",
|
35 |
+
"no_aggregation_label_index": 0,
|
36 |
+
"num_aggregation_labels": 4,
|
37 |
+
"num_attention_heads": 12,
|
38 |
+
"num_hidden_layers": 12,
|
39 |
+
"pad_token_id": 0,
|
40 |
+
"positive_label_weight": 10.0,
|
41 |
+
"reset_position_index_per_cell": true,
|
42 |
+
"select_one_column": true,
|
43 |
+
"softmax_temperature": 1.0,
|
44 |
+
"temperature": 0.0352513,
|
45 |
+
"transformers_version": "4.25.1",
|
46 |
+
"type_vocab_size": [
|
47 |
+
3,
|
48 |
+
256,
|
49 |
+
256,
|
50 |
+
2,
|
51 |
+
256,
|
52 |
+
256,
|
53 |
+
10
|
54 |
+
],
|
55 |
+
"type_vocab_sizes": [
|
56 |
+
3,
|
57 |
+
256,
|
58 |
+
256,
|
59 |
+
2,
|
60 |
+
256,
|
61 |
+
256,
|
62 |
+
10
|
63 |
+
],
|
64 |
+
"use_answer_as_supervision": true,
|
65 |
+
"use_gumbel_for_aggregation": false,
|
66 |
+
"use_gumbel_for_cells": false,
|
67 |
+
"use_normalized_answer_loss": false,
|
68 |
+
"vocab_size": 30522
|
69 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe28b90325c7bc74534431375095e4e0e9fac622c720cfe5246fb0ec270025fe
|
3 |
+
size 443010576
|