isbondarev commited on
Commit
357bab0
·
verified ·
1 Parent(s): dcd50c1

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,28 +1,3 @@
1
  {
2
- "</think>": 151668,
3
- "</tool_call>": 151658,
4
- "</tool_response>": 151666,
5
- "<think>": 151667,
6
- "<tool_call>": 151657,
7
- "<tool_response>": 151665,
8
- "<|box_end|>": 151649,
9
- "<|box_start|>": 151648,
10
- "<|endoftext|>": 151643,
11
- "<|file_sep|>": 151664,
12
- "<|fim_middle|>": 151660,
13
- "<|fim_pad|>": 151662,
14
- "<|fim_prefix|>": 151659,
15
- "<|fim_suffix|>": 151661,
16
- "<|im_end|>": 151645,
17
- "<|im_start|>": 151644,
18
- "<|image_pad|>": 151655,
19
- "<|object_ref_end|>": 151647,
20
- "<|object_ref_start|>": 151646,
21
- "<|quad_end|>": 151651,
22
- "<|quad_start|>": 151650,
23
- "<|repo_name|>": 151663,
24
- "<|video_pad|>": 151656,
25
- "<|vision_end|>": 151653,
26
- "<|vision_pad|>": 151654,
27
- "<|vision_start|>": 151652
28
  }
 
1
  {
2
+ "<image_soft_token>": 262144
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  }
chat_template.jinja CHANGED
@@ -1,89 +1,47 @@
1
- {%- if tools %}
2
- {{- '<|im_start|>system\n' }}
3
- {%- if messages[0].role == 'system' %}
4
- {{- messages[0].content + '\n\n' }}
5
- {%- endif %}
6
- {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
- {%- for tool in tools %}
8
- {{- "\n" }}
9
- {{- tool | tojson }}
10
- {%- endfor %}
11
- {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
- {%- else %}
13
- {%- if messages[0].role == 'system' %}
14
- {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
- {%- endif %}
16
- {%- endif %}
17
- {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
- {%- for message in messages[::-1] %}
19
- {%- set index = (messages|length - 1) - loop.index0 %}
20
- {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
- {%- set ns.multi_step_tool = false %}
22
- {%- set ns.last_query_index = index %}
23
- {%- endif %}
24
- {%- endfor %}
25
- {%- for message in messages %}
26
- {%- if message.content is string %}
27
- {%- set content = message.content %}
28
- {%- else %}
29
- {%- set content = '' %}
30
- {%- endif %}
31
- {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
- {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
- {%- elif message.role == "assistant" %}
34
- {%- set reasoning_content = '' %}
35
- {%- if message.reasoning_content is string %}
36
- {%- set reasoning_content = message.reasoning_content %}
37
- {%- else %}
38
- {%- if '</think>' in content %}
39
- {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
- {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
- {%- endif %}
42
- {%- endif %}
43
- {%- if loop.index0 > ns.last_query_index %}
44
- {%- if loop.last or (not loop.last and reasoning_content) %}
45
- {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
- {%- else %}
47
- {{- '<|im_start|>' + message.role + '\n' + content }}
48
- {%- endif %}
49
- {%- else %}
50
- {{- '<|im_start|>' + message.role + '\n' + content }}
51
- {%- endif %}
52
- {%- if message.tool_calls %}
53
- {%- for tool_call in message.tool_calls %}
54
- {%- if (loop.first and content) or (not loop.first) %}
55
- {{- '\n' }}
56
- {%- endif %}
57
- {%- if tool_call.function %}
58
- {%- set tool_call = tool_call.function %}
59
- {%- endif %}
60
- {{- '<tool_call>\n{"name": "' }}
61
- {{- tool_call.name }}
62
- {{- '", "arguments": ' }}
63
- {%- if tool_call.arguments is string %}
64
- {{- tool_call.arguments }}
65
- {%- else %}
66
- {{- tool_call.arguments | tojson }}
67
- {%- endif %}
68
- {{- '}\n</tool_call>' }}
69
- {%- endfor %}
70
- {%- endif %}
71
- {{- '<|im_end|>\n' }}
72
- {%- elif message.role == "tool" %}
73
- {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
- {{- '<|im_start|>user' }}
75
- {%- endif %}
76
- {{- '\n<tool_response>\n' }}
77
- {{- content }}
78
- {{- '\n</tool_response>' }}
79
- {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
- {{- '<|im_end|>\n' }}
81
- {%- endif %}
82
- {%- endif %}
83
- {%- endfor %}
84
- {%- if add_generation_prompt %}
85
- {{- '<|im_start|>assistant\n' }}
86
- {%- if enable_thinking is defined and enable_thinking is false %}
87
- {{- '<think>\n\n</think>\n\n' }}
88
- {%- endif %}
89
- {%- endif %}
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<start_of_turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<start_of_image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<end_of_turn>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<start_of_turn>model
46
+ '}}
47
+ {%- endif -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json CHANGED
@@ -1,28 +1,30 @@
1
  {
2
- "additional_special_tokens": [
3
- "<|im_start|>",
4
- "<|im_end|>",
5
- "<|object_ref_start|>",
6
- "<|object_ref_end|>",
7
- "<|box_start|>",
8
- "<|box_end|>",
9
- "<|quad_start|>",
10
- "<|quad_end|>",
11
- "<|vision_start|>",
12
- "<|vision_end|>",
13
- "<|vision_pad|>",
14
- "<|image_pad|>",
15
- "<|video_pad|>"
16
- ],
17
  "eos_token": {
18
- "content": "<|im_end|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  },
 
24
  "pad_token": {
25
- "content": "<|endoftext|>",
 
 
 
 
 
 
 
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
 
1
  {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
 
 
 
 
 
 
11
  "eos_token": {
12
+ "content": "<end_of_turn>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false
17
  },
18
+ "image_token": "<image_soft_token>",
19
  "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
  "lstrip": false,
29
  "normalized": false,
30
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
- size 11422654
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
3
+ size 33384568
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff