Commit
•
4ea7c76
1
Parent(s):
3c589a4
add model
Browse files- config.json +10 -17
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,6 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "google/tapas-
|
| 3 |
-
"activation": "gelu",
|
| 4 |
"aggregation_labels": null,
|
| 5 |
"aggregation_loss_weight": 1.0,
|
| 6 |
"aggregation_temperature": 1.0,
|
|
@@ -8,43 +7,37 @@
|
|
| 8 |
"answer_loss_cutoff": null,
|
| 9 |
"answer_loss_importance": 1.0,
|
| 10 |
"architectures": [
|
| 11 |
-
"
|
| 12 |
],
|
| 13 |
-
"
|
| 14 |
-
"attention_probs_dropout_prob": 0.0,
|
| 15 |
"average_approximation_function": "ratio",
|
| 16 |
"average_logits_per_cell": false,
|
| 17 |
"cell_selection_preference": null,
|
| 18 |
-
"dim": 768,
|
| 19 |
"disable_per_token_loss": false,
|
| 20 |
-
"dropout": 0.1,
|
| 21 |
"gradient_checkpointing": false,
|
| 22 |
"hidden_act": "gelu",
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
"huber_loss_delta": null,
|
| 26 |
"init_cell_selection_weights_to_zero": false,
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
-
"intermediate_size":
|
| 29 |
"layer_norm_eps": 1e-12,
|
| 30 |
"max_num_columns": 32,
|
| 31 |
"max_num_rows": 64,
|
| 32 |
"max_position_embeddings": 1024,
|
| 33 |
-
"model_type": "
|
| 34 |
-
"n_heads": 12,
|
| 35 |
-
"n_layers": 12,
|
| 36 |
"no_aggregation_label_index": null,
|
| 37 |
"num_aggregation_labels": 0,
|
|
|
|
|
|
|
| 38 |
"pad_token_id": 0,
|
| 39 |
"positive_label_weight": 10.0,
|
| 40 |
-
"qa_dropout": 0.1,
|
| 41 |
"reset_position_index_per_cell": true,
|
| 42 |
"select_one_column": true,
|
| 43 |
-
"seq_classif_dropout": 0.2,
|
| 44 |
-
"sinusoidal_pos_embds": false,
|
| 45 |
"softmax_temperature": 1.0,
|
| 46 |
"torch_dtype": "float32",
|
| 47 |
-
"transformers_version": "4.
|
| 48 |
"type_vocab_size": [
|
| 49 |
3,
|
| 50 |
256,
|
|
|
|
| 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,
|
|
|
|
| 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": "4.16.0.dev0",
|
| 41 |
"type_vocab_size": [
|
| 42 |
3,
|
| 43 |
256,
|
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 sha256:95e6c8ac7fbd313c1fe1d231e691c1501b8cafcb6dfd3ea7e78772d33138b518
|
| 3 |
+
size 1347091016
|