revert (3) tokenizer files commits
Browse files- .gitattributes +0 -1
- config.json +0 -6
- special_tokens_map.json +1 -15
- tokenizer.json +0 -3
- tokenizer_config.json +1 -19
.gitattributes
CHANGED
@@ -6,4 +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.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
|
|
config.json
CHANGED
@@ -1,11 +1,9 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "joeddav/xlm-roberta-large-xnli",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": null,
|
9 |
"eos_token_id": 2,
|
10 |
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
@@ -30,10 +28,6 @@
|
|
30 |
"num_hidden_layers": 24,
|
31 |
"output_past": true,
|
32 |
"pad_token_id": 1,
|
33 |
-
"position_embedding_type": "absolute",
|
34 |
-
"torch_dtype": "float32",
|
35 |
-
"transformers_version": "4.27.2",
|
36 |
"type_vocab_size": 1,
|
37 |
-
"use_cache": true,
|
38 |
"vocab_size": 250002
|
39 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"XLMRobertaForSequenceClassification"
|
4 |
],
|
5 |
"attention_probs_dropout_prob": 0.1,
|
6 |
"bos_token_id": 0,
|
|
|
7 |
"eos_token_id": 2,
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
|
|
28 |
"num_hidden_layers": 24,
|
29 |
"output_past": true,
|
30 |
"pad_token_id": 1,
|
|
|
|
|
|
|
31 |
"type_vocab_size": 1,
|
|
|
32 |
"vocab_size": 250002
|
33 |
}
|
special_tokens_map.json
CHANGED
@@ -1,15 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
3 |
-
size 17082660
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
@@ -1,19 +1 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"__type": "AddedToken",
|
7 |
-
"content": "<mask>",
|
8 |
-
"lstrip": true,
|
9 |
-
"normalized": true,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"model_max_length": 512,
|
14 |
-
"pad_token": "<pad>",
|
15 |
-
"sep_token": "</s>",
|
16 |
-
"special_tokens_map_file": null,
|
17 |
-
"tokenizer_class": "XLMRobertaTokenizer",
|
18 |
-
"unk_token": "<unk>"
|
19 |
-
}
|
|
|
1 |
+
{"model_max_length": 512}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|