Commit
·
7c1c04e
1
Parent(s):
bd07c18
Upload tokenizer
Browse files- special_tokens_map.json +13 -0
- tokenizer.model +3 -0
- tokenizer_config.json +9 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<SN>",
|
4 |
+
"<EN>",
|
5 |
+
"</s>",
|
6 |
+
"<SN>",
|
7 |
+
"<EN>"
|
8 |
+
],
|
9 |
+
"bos_token": "</s>",
|
10 |
+
"eos_token": "</s>",
|
11 |
+
"pad_token": "</s>",
|
12 |
+
"unk_token": "</s>"
|
13 |
+
}
|
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 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "",
|
3 |
+
"eos_token": "",
|
4 |
+
"model_max_length": 512,
|
5 |
+
"padding_side": "right",
|
6 |
+
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--decapoda-research--llama-7b-hf/snapshots/5f98eefcc80e437ef68d457ad7bf167c2c6a1348/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "LlamaTokenizer",
|
8 |
+
"unk_token": ""
|
9 |
+
}
|