Upload tokenizer
Browse files- added_tokens.json +5 -0
- merges.txt +0 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}<|im_start|>system\n{% if builtin_tools is defined or tools is not none %}Environment: ipython\n{% endif %}{% if builtin_tools is defined %}Tools: {{ builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") }}\n{% endif %}Cutting Knowledge Date: December 2023\nToday Date: {{ date_string | default(\"26 Jul 2024\") }}\n\n{% if tools is not none and not tools_in_user_message %}You have access to the following functions. To call a function, please respond with JSON for a function call.\nRespond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.\nDo not use variables.\n\n{% for t in tools %}{{ t | tojson(indent=4) }}\n\n{% endfor %}{% endif %}{{ messages[0]['content']|trim }}<|im_end|>\n\n{% set messages = messages[1:] %}{% endif %}{% for message in messages %}{% if message.role == 'user' or message.role == 'assistant' %}<|im_start|>{{ message['role'] }}\n{{ message['content'] | trim }}<|im_end|>\n\n{% elif 'tool_calls' in message %}<|im_start|>assistant\n{% set tool_call = message.tool_calls[0].function %}{% if builtin_tools is defined and tool_call.name in builtin_tools %}<|python_tag|>{{ tool_call.name }}.call({% for arg_name, arg_val in tool_call.arguments | items %}{{ arg_name }}=\"{{ arg_val }}\"{% if not loop.last %}, {% endif %}{% endfor %}){% else %}{\"name\": \"{{ tool_call.name }}\", \"parameters\": {{ tool_call.arguments | tojson }}}{% endif %}<|im_end|>\n\n{% elif message.role == \"tool\" or message.role == \"ipython\" %}<|im_start|>ipython\n{% if message.content is mapping or message.content is iterable %}{{ message.content | tojson }}{% else %}{{ message.content }}{% endif %}<|im_end|>\n\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"padding_side": "left",
|
41 |
+
"split_special_tokens": false,
|
42 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
43 |
+
"unk_token": null
|
44 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|