Upload 3 files
Browse files- special_tokens_map.json +7 -0
- tokenizer.model +3 -0
- tokenizer_config.json +12 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<unk>",
|
5 |
+
"sep_token": "<s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"tokenizer_class": "LlamaTokenizer",
|
3 |
+
"model_max_length": 2048,
|
4 |
+
"padding_side": "left",
|
5 |
+
"add_bos_token": false,
|
6 |
+
"add_eos_token": false,
|
7 |
+
"bos_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"unk_token": "<unk>",
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"special_tokens_map_file": "special_tokens_map.json"
|
12 |
+
}
|