Upload 8 files
Browse files
converted_tokenizer/special_tokens_map.json
CHANGED
@@ -1,5 +1,30 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": true,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": true,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": true,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": true,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": true,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": true,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
converted_tokenizer/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
converted_tokenizer/tokenizer_config.json
CHANGED
@@ -774,7 +774,9 @@
|
|
774 |
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
|
775 |
"clean_up_tokenization_spaces": false,
|
776 |
"eos_token": "<|endoftext|>",
|
|
|
777 |
"model_max_length": 16384,
|
778 |
"pad_token": "<|endoftext|>",
|
779 |
-
"tokenizer_class": "GPT2Tokenizer"
|
780 |
-
|
|
|
|
774 |
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|><|im_start|>assistant<|im_sep|>'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}",
|
775 |
"clean_up_tokenization_spaces": false,
|
776 |
"eos_token": "<|endoftext|>",
|
777 |
+
"extra_special_tokens": {},
|
778 |
"model_max_length": 16384,
|
779 |
"pad_token": "<|endoftext|>",
|
780 |
+
"tokenizer_class": "GPT2Tokenizer",
|
781 |
+
"unk_token": "<|endoftext|>"
|
782 |
+
}
|
converted_tokenizer/vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|