Upload tokenizer
Browse files- added_tokens.json +7 -0
- special_tokens_map.json +12 -0
- tokenizer.model +3 -0
- tokenizer_config.json +9 -0
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|assistant|>": 32002,
|
3 |
+
"<|prefix_begin|>": 32000,
|
4 |
+
"<|prefix_end|>": 32001,
|
5 |
+
"<|prompter|>": 32003,
|
6 |
+
"<|system|>": 32004
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|prompter|>",
|
4 |
+
"<|prefix_end|>",
|
5 |
+
"<|system|>",
|
6 |
+
"<|assistant|>",
|
7 |
+
"<|prefix_begin|>"
|
8 |
+
],
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"pad_token": "</s>",
|
11 |
+
"sep_token": "<s>"
|
12 |
+
}
|
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 |
+
"clean_up_tokenization_spaces": false,
|
4 |
+
"eos_token": "",
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"special_tokens_map_file": "/home/ubuntu/llama_hf/13B/special_tokens_map.json",
|
7 |
+
"tokenizer_class": "LlamaTokenizer",
|
8 |
+
"unk_token": ""
|
9 |
+
}
|