Commit
•
a164575
1
Parent(s):
21d5dd8
Training in progress epoch 0
Browse files- config.json +1 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -7
- tokenizer_config.json +1 -16
config.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"summary_type": "first",
|
24 |
"summary_use_proj": true,
|
25 |
"torch_dtype": "float32",
|
26 |
-
"transformers_version": "4.
|
27 |
"type_vocab_size": 2,
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32000
|
|
|
23 |
"summary_type": "first",
|
24 |
"summary_use_proj": true,
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.17.0",
|
27 |
"type_vocab_size": 2,
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 32000
|
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 sha256:0c6be860c96d76dd8770867653edc6b00cd75b709f5b44f053cb6dcb7e953450
|
3 |
+
size 440200493
|
special_tokens_map.json
CHANGED
@@ -1,7 +1 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer_config.json
CHANGED
@@ -1,16 +1 @@
|
|
1 |
-
{
|
2 |
-
"clean_up_tokenization_spaces": true,
|
3 |
-
"cls_token": "[CLS]",
|
4 |
-
"do_basic_tokenize": true,
|
5 |
-
"do_lower_case": false,
|
6 |
-
"full_tokenizer_file": null,
|
7 |
-
"mask_token": "[MASK]",
|
8 |
-
"model_max_length": 1000000000000000019884624838656,
|
9 |
-
"never_split": null,
|
10 |
-
"pad_token": "[PAD]",
|
11 |
-
"sep_token": "[SEP]",
|
12 |
-
"strip_accents": null,
|
13 |
-
"tokenize_chinese_chars": false,
|
14 |
-
"tokenizer_class": "ElectraTokenizer",
|
15 |
-
"unk_token": "[UNK]"
|
16 |
-
}
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": false, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "csebuetnlp/banglabert", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|