Julien Chaumond
commited on
Commit
•
1a54e86
1
Parent(s):
66cbc8c
Textual files shouldn't be stored in LFS
Browse files- .gitattributes +0 -7
- README.md +3 -3
- config.json +28 -3
- special_tokens_map.json +1 -3
- tokenizer_config.json +1 -3
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -6,10 +6,3 @@
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
-
tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
|
10 |
-
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
11 |
-
vocab.txt filter=lfs diff=lfs merge=lfs -text
|
12 |
-
config.json filter=lfs diff=lfs merge=lfs -text
|
13 |
-
pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
|
14 |
-
README.md filter=lfs diff=lfs merge=lfs -text
|
15 |
-
special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
|
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
CHANGED
@@ -3,11 +3,11 @@ language:
|
|
3 |
- pt-br
|
4 |
tags:
|
5 |
- question-answering
|
6 |
-
license:
|
7 |
pipeline_tag: question-answering
|
8 |
metrics:
|
9 |
-
-
|
10 |
-
-
|
11 |
---
|
12 |
|
13 |
# BraQuAD BERT
|
|
|
3 |
- pt-br
|
4 |
tags:
|
5 |
- question-answering
|
6 |
+
license: apache-2.0
|
7 |
pipeline_tag: question-answering
|
8 |
metrics:
|
9 |
+
- em
|
10 |
+
- f1
|
11 |
---
|
12 |
|
13 |
# BraQuAD BERT
|
config.json
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"output_past": true,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pooler_fc_size": 768,
|
22 |
+
"pooler_num_attention_heads": 12,
|
23 |
+
"pooler_num_fc_layers": 3,
|
24 |
+
"pooler_size_per_head": 128,
|
25 |
+
"pooler_type": "first_token_transform",
|
26 |
+
"type_vocab_size": 2,
|
27 |
+
"vocab_size": 29794
|
28 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,3 +1 @@
|
|
1 |
-
|
2 |
-
oid sha256:303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3
|
3 |
-
size 112
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
|
|
|
tokenizer_config.json
CHANGED
@@ -1,3 +1 @@
|
|
1 |
-
|
2 |
-
oid sha256:27b115b415379b1d222275b55a76dcb2c50b5935600c12832dd9716fb8f5ad79
|
3 |
-
size 512
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/root/.cache/torch/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null, "name_or_path": "neuralmind/bert-base-portuguese-cased"}
|
|
|
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|