danielhanchen commited on
Commit
e4db6bc
·
verified ·
1 Parent(s): fce6516

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</minimax:tool_call>": 200053,
3
+ "</think>": 200051,
4
+ "<add_file>": 200036,
5
+ "<code_context>": 200043,
6
+ "<code_interpreter>": 200023,
7
+ "<commit_after>": 200018,
8
+ "<commit_before>": 200016,
9
+ "<commit_message>": 200040,
10
+ "<commit_msg>": 200017,
11
+ "<delete_file>": 200037,
12
+ "<edit_file>": 200039,
13
+ "<empty_output>": 200015,
14
+ "<empty_source_file>": 200041,
15
+ "<file_content>": 200044,
16
+ "<file_sep>": 200049,
17
+ "<filename>": 200006,
18
+ "<filepath>": 200048,
19
+ "<fim_middle>": 200002,
20
+ "<fim_pad>": 200004,
21
+ "<fim_prefix>": 200001,
22
+ "<fim_suffix>": 200003,
23
+ "<function_call>": 200022,
24
+ "<gh_stars>": 200007,
25
+ "<issue_closed>": 200010,
26
+ "<issue_comment>": 200009,
27
+ "<issue_start>": 200008,
28
+ "<jupyter_code>": 200013,
29
+ "<jupyter_error>": 200035,
30
+ "<jupyter_output>": 200014,
31
+ "<jupyter_start>": 200011,
32
+ "<jupyter_text>": 200012,
33
+ "<minimax:tool_call>": 200052,
34
+ "<pr_start>": 200046,
35
+ "<rename_file>": 200038,
36
+ "<repo_struct>": 200042,
37
+ "<reponame>": 200005,
38
+ "<review_comment>": 200047,
39
+ "<source_files>": 200045,
40
+ "<think>": 200050,
41
+ "[e~[": 200020,
42
+ "]!d~[": 200021,
43
+ "]!p~[": 200000,
44
+ "]<]end of image[>[": 200030,
45
+ "]<]end of speech[>[": 200028,
46
+ "]<]end of video[>[": 200032,
47
+ "]<]image[>[": 200025,
48
+ "]<]speech[>[": 200024,
49
+ "]<]start of image[>[": 200029,
50
+ "]<]start of speech[>[": 200027,
51
+ "]<]start of video[>[": 200031,
52
+ "]<]video[>[": 200026,
53
+ "]<]vision pad[>[": 200033,
54
+ "]~!b[": 200034,
55
+ "]~b]": 200019
56
+ }
config.json CHANGED
@@ -114,7 +114,7 @@
114
  "shared_intermediate_size": 0,
115
  "sliding_window": null,
116
  "tie_word_embeddings": false,
117
- "transformers_version": "5.1.0",
118
  "unsloth_fixed": true,
119
  "use_cache": true,
120
  "use_mtp": true,
 
114
  "shared_intermediate_size": 0,
115
  "sliding_window": null,
116
  "tie_word_embeddings": false,
117
+ "transformers_version": "4.57.6",
118
  "unsloth_fixed": true,
119
  "use_cache": true,
120
  "use_mtp": true,
merges.txt CHANGED
@@ -199742,4 +199742,4 @@ ch ile
199742
  ع اÙĨ
199743
  Ġdel ving
199744
  Ġت ÙĥÙĪÙĬÙĨ
199745
- .ch romium
 
199742
  ع اÙĨ
199743
  Ġdel ving
199744
  Ġت ÙĥÙĪÙĬÙĨ
199745
+ .ch romium
special_tokens_map.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<code_interpreter>",
4
+ "<commit_after>",
5
+ "<commit_before>",
6
+ "<commit_msg>",
7
+ "<empty_output>",
8
+ "<filename>",
9
+ "<fim_middle>",
10
+ "<fim_pad>",
11
+ "<fim_prefix>",
12
+ "<fim_suffix>",
13
+ "<function_call>",
14
+ "<gh_stars>",
15
+ "]<]speech[>[",
16
+ "]<]image[>[",
17
+ "]<]video[>[",
18
+ "]<]start of speech[>[",
19
+ "]<]end of speech[>[",
20
+ "]<]start of image[>[",
21
+ "]<]end of image[>[",
22
+ "]<]start of video[>[",
23
+ "]<]end of video[>[",
24
+ "]<]vision pad[>[",
25
+ "]~!b[",
26
+ "<issue_closed>",
27
+ "<issue_comment>",
28
+ "<issue_start>",
29
+ "<jupyter_code>",
30
+ "<jupyter_output>",
31
+ "<jupyter_start>",
32
+ "<jupyter_text>",
33
+ "<reponame>",
34
+ "[e~[",
35
+ "]!d~[",
36
+ "]!p~[",
37
+ "]~b]",
38
+ "<jupyter_error>",
39
+ "<add_file>",
40
+ "<delete_file>",
41
+ "<rename_file>",
42
+ "<edit_file>",
43
+ "<commit_message>",
44
+ "<empty_source_file>",
45
+ "<repo_struct>",
46
+ "<code_context>",
47
+ "<file_content>",
48
+ "<source_files>",
49
+ "<pr_start>",
50
+ "<review_comment>",
51
+ "<filepath>",
52
+ "<file_sep>"
53
+ ],
54
+ "bos_token": {
55
+ "content": "]~!b[",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false
60
+ },
61
+ "eos_token": {
62
+ "content": "[e~[",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "pad_token": {
69
+ "content": "<fim_pad>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false
74
+ },
75
+ "unk_token": {
76
+ "content": "]!d~[",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false
81
+ }
82
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9e59eadb3e8ccfba9dee9d16af6a9241809826d58cd4a5eac8ff0c6f8619330
3
- size 15523593
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7b90ed7f55d905175bc26771d6d7d33b40b46742f073675bc816fedaf482ea1
3
+ size 15522763
tokenizer_config.json CHANGED
@@ -1,10 +1,441 @@
1
  {
 
2
  "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": "]~!b[",
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "[e~[",
7
- "extra_special_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "<code_interpreter>",
9
  "<commit_after>",
10
  "<commit_before>",
@@ -56,11 +487,14 @@
56
  "<filepath>",
57
  "<file_sep>"
58
  ],
59
- "is_local": true,
 
 
 
60
  "model_max_length": 196608,
61
  "pad_token": "<fim_pad>",
62
  "padding_side": "left",
63
- "tokenizer_class": "TokenizersBackend",
64
  "unk_token": "]!d~[",
65
  "chat_template": "{# Unsloth template fixes #}\n{# ----------‑‑‑ special token variables ‑‑‑---------- #}\n{%- set toolcall_begin_token = '<minimax:tool_call>' -%}\n{%- set toolcall_end_token = '</minimax:tool_call>' -%}\n{#- Tool Rendering Functions ============================================== -#}\n{%- macro render_tool_namespace(namespace_name, tool_list) -%}\n{%- for tool in tool_list -%}\n<tool>{{ (tool.function if tool.function is defined else tool) | tojson(ensure_ascii=False) }}</tool>\n{% endfor -%}\n{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{ content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{#- System Message Construction ============================================ -#}\n{%- macro build_system_message(system_message) -%}\n {%- if system_message and system_message.content -%}\n {{- visible_text(system_message.content) }}\n {%- else -%}\n {%- if model_identity is not defined -%}\n {%- set model_identity = \"You are a helpful assistant. Your name is MiniMax-M2.5 and is built by MiniMax.\" -%}\n {%- endif -%}\n {{- model_identity }}\n {%- endif -%}\n \n {#- Handle current_date -#}\n {%- if system_message and system_message.current_date -%}\n {{- '\\n' ~ 'Current date: ' + system_message.current_date }}\n {%- endif -%}\n {#- Handle current_location -#}\n {%- if system_message and system_message.current_location -%}\n {{- '\\n' ~ 'Current location: ' + system_message.current_location }}\n {%- endif -%}\n{%- endmacro -%}\n{#- Main Template Logic ================================================= -#}\n{#- Extract system message (only first message if it's system) -#}\n{%- set system_message = none -%}\n{%- set conversation_messages = messages -%}\n{%- if messages and messages[0].role == \"system\" -%}\n {%- set system_message = messages[0] -%}\n {%- set conversation_messages = messages[1:] -%}\n{%- endif -%}\n{#- Get the last user message turn, for interleved thinking -#}\n{%- set ns = namespace(last_user_index=-1) %}\n{% for m in conversation_messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{#- Render system message -#}\n{{- ']~!b[' ~ ']~b]system' ~ '\\n' }}\n{{- build_system_message(system_message) }}\n{#- Render tools if available -#}\n{%- if tools -%}\n {{- '\\n\\n' ~ '# Tools' ~ '\\n' ~ 'You may call one or more tools to assist with the user query.\\nHere are the tools available in JSONSchema format:' ~ '\\n' }}\n {{- '\\n' ~ '<tools>' ~ '\\n' }}\n {{- render_tool_namespace(\"functions\", tools) }}\n {{- '</tools>' ~ '\\n\\n' }}\n{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\\n' }}\n{{- '\\n' ~ toolcall_begin_token }}\n<invoke name=\"tool-name-1\">\n<parameter name=\"param-key-1\">param-value-1</parameter>\n<parameter name=\"param-key-2\">param-value-2</parameter>\n...\n</invoke>\n{{- '\\n' ~ toolcall_end_token }}\n{%- endif -%}\n{{- '[e~[\\n' }}\n\n{#- Render messages -#}\n{%- set last_tool_call = namespace(name=none) -%}\n{%- for message in conversation_messages -%}\n {%- if message.role == 'assistant' -%}\n {#- Only render reasoning_content if no user message follows -#}\n {{- ']~b]ai' ~ '\\n' }}\n\n {%- set reasoning_content = '' %}\n {%- set content = visible_text(message.content) %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].strip('\\n').split('<think>')[-1].strip('\\n') %}\n {%- set content = content.split('</think>')[-1].strip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if reasoning_content and loop.index0 > ns.last_user_index -%}\n {{- '<think>' ~ '\\n' ~ reasoning_content ~ '\\n' ~ '</think>' ~ '\\n\\n' }}\n {%- endif -%}\n {%- if content -%}\n {{- content }}\n {%- endif -%}\n {%- if message.tool_calls -%}\n {{- '\\n' ~ toolcall_begin_token ~ '\\n' }}\n\n {%- for tool_call in message.tool_calls -%}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<invoke name=\"' + tool_call.name + '\">' }}\n {% set _args = tool_call.arguments %}\n {%- for k, v in _args.items() %}\n {{- '<parameter name=\"' + k + '\">' }}\n {{- v | tojson(ensure_ascii=False) if v is not string else v }}\n {{- '</parameter>' }}\n {% endfor %}\n {{- '</invoke>' ~ '\\n' }}\n {%- endfor -%}\n \n {{- toolcall_end_token}}\n {%- set last_tool_call.name = message.tool_calls[-1].name -%}\n {%- else -%}\n {%- set last_tool_call.name = none -%}\n {%- endif -%}\n {{- '[e~[' ~ '\\n' }}\n \n {%- elif message.role == 'tool' -%}\n {%- if last_tool_call.name is none -%}\n {{- raise_exception(\"Message has tool role, but there was no previous assistant message with a tool call!\") }}\n {%- endif -%}\n {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}\n {{- ']~b]tool' }}\n {%- endif -%}\n {%- if message.content is string -%}\n {{- '\\n<response>' }}\n {{- message.content }}\n {{- '</response>' }}\n {%- else -%}\n {%- for tr in message.content -%}\n {{- '\\n<response>' }}\n {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}\n {{- '\\n</response>' }}\n {%- endfor -%}\n {%- endif -%}\n {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}\n {{- '[e~[\\n' -}}\n {%- endif -%}\n \n {%- elif message.role == 'user' -%}\n {{- ']~b]user' ~ '\\n' }}\n {{- visible_text(message.content) }}\n {{- '[e~[' ~ '\\n' }}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Generation prompt -#}\n{%- if add_generation_prompt -%}\n{{- ']~b]ai' ~ '\\n' ~ '<think>' ~ '\\n' }}\n{%- endif -%}\n\n{# Copyright 2025-present Unsloth. Apache 2.0 License. #}"
66
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "200000": {
6
+ "content": "]!p~[",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "200001": {
14
+ "content": "<fim_prefix>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "200002": {
22
+ "content": "<fim_middle>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "200003": {
30
+ "content": "<fim_suffix>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "200004": {
38
+ "content": "<fim_pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "200005": {
46
+ "content": "<reponame>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "200006": {
54
+ "content": "<filename>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "200007": {
62
+ "content": "<gh_stars>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "200008": {
70
+ "content": "<issue_start>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "200009": {
78
+ "content": "<issue_comment>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "200010": {
86
+ "content": "<issue_closed>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "200011": {
94
+ "content": "<jupyter_start>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "200012": {
102
+ "content": "<jupyter_text>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "200013": {
110
+ "content": "<jupyter_code>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "200014": {
118
+ "content": "<jupyter_output>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "200015": {
126
+ "content": "<empty_output>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "200016": {
134
+ "content": "<commit_before>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "200017": {
142
+ "content": "<commit_msg>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "200018": {
150
+ "content": "<commit_after>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "200019": {
158
+ "content": "]~b]",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "200020": {
166
+ "content": "[e~[",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "200021": {
174
+ "content": "]!d~[",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "200022": {
182
+ "content": "<function_call>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "200023": {
190
+ "content": "<code_interpreter>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "200024": {
198
+ "content": "]<]speech[>[",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "200025": {
206
+ "content": "]<]image[>[",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "200026": {
214
+ "content": "]<]video[>[",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "200027": {
222
+ "content": "]<]start of speech[>[",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "200028": {
230
+ "content": "]<]end of speech[>[",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "200029": {
238
+ "content": "]<]start of image[>[",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "200030": {
246
+ "content": "]<]end of image[>[",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "200031": {
254
+ "content": "]<]start of video[>[",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "200032": {
262
+ "content": "]<]end of video[>[",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "200033": {
270
+ "content": "]<]vision pad[>[",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "200034": {
278
+ "content": "]~!b[",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "200035": {
286
+ "content": "<jupyter_error>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "200036": {
294
+ "content": "<add_file>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "200037": {
302
+ "content": "<delete_file>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "200038": {
310
+ "content": "<rename_file>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "200039": {
318
+ "content": "<edit_file>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "200040": {
326
+ "content": "<commit_message>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "200041": {
334
+ "content": "<empty_source_file>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "200042": {
342
+ "content": "<repo_struct>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "200043": {
350
+ "content": "<code_context>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "200044": {
358
+ "content": "<file_content>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "200045": {
366
+ "content": "<source_files>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "200046": {
374
+ "content": "<pr_start>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "200047": {
382
+ "content": "<review_comment>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "200048": {
390
+ "content": "<filepath>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "200049": {
398
+ "content": "<file_sep>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "200050": {
406
+ "content": "<think>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": false
412
+ },
413
+ "200051": {
414
+ "content": "</think>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": false
420
+ },
421
+ "200052": {
422
+ "content": "<minimax:tool_call>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": false
428
+ },
429
+ "200053": {
430
+ "content": "</minimax:tool_call>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": false
436
+ }
437
+ },
438
+ "additional_special_tokens": [
439
  "<code_interpreter>",
440
  "<commit_after>",
441
  "<commit_before>",
 
487
  "<filepath>",
488
  "<file_sep>"
489
  ],
490
+ "bos_token": "]~!b[",
491
+ "clean_up_tokenization_spaces": false,
492
+ "eos_token": "[e~[",
493
+ "extra_special_tokens": {},
494
  "model_max_length": 196608,
495
  "pad_token": "<fim_pad>",
496
  "padding_side": "left",
497
+ "tokenizer_class": "GPT2Tokenizer",
498
  "unk_token": "]!d~[",
499
  "chat_template": "{# Unsloth template fixes #}\n{# ----------‑‑‑ special token variables ‑‑‑---------- #}\n{%- set toolcall_begin_token = '<minimax:tool_call>' -%}\n{%- set toolcall_end_token = '</minimax:tool_call>' -%}\n{#- Tool Rendering Functions ============================================== -#}\n{%- macro render_tool_namespace(namespace_name, tool_list) -%}\n{%- for tool in tool_list -%}\n<tool>{{ (tool.function if tool.function is defined else tool) | tojson(ensure_ascii=False) }}</tool>\n{% endfor -%}\n{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{ content }}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text }}\n {%- elif item is string -%}\n {{- item }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{#- System Message Construction ============================================ -#}\n{%- macro build_system_message(system_message) -%}\n {%- if system_message and system_message.content -%}\n {{- visible_text(system_message.content) }}\n {%- else -%}\n {%- if model_identity is not defined -%}\n {%- set model_identity = \"You are a helpful assistant. Your name is MiniMax-M2.5 and is built by MiniMax.\" -%}\n {%- endif -%}\n {{- model_identity }}\n {%- endif -%}\n \n {#- Handle current_date -#}\n {%- if system_message and system_message.current_date -%}\n {{- '\\n' ~ 'Current date: ' + system_message.current_date }}\n {%- endif -%}\n {#- Handle current_location -#}\n {%- if system_message and system_message.current_location -%}\n {{- '\\n' ~ 'Current location: ' + system_message.current_location }}\n {%- endif -%}\n{%- endmacro -%}\n{#- Main Template Logic ================================================= -#}\n{#- Extract system message (only first message if it's system) -#}\n{%- set system_message = none -%}\n{%- set conversation_messages = messages -%}\n{%- if messages and messages[0].role == \"system\" -%}\n {%- set system_message = messages[0] -%}\n {%- set conversation_messages = messages[1:] -%}\n{%- endif -%}\n{#- Get the last user message turn, for interleved thinking -#}\n{%- set ns = namespace(last_user_index=-1) %}\n{% for m in conversation_messages %}\n {%- if m.role == 'user' %}\n {% set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{#- Render system message -#}\n{{- ']~!b[' ~ ']~b]system' ~ '\\n' }}\n{{- build_system_message(system_message) }}\n{#- Render tools if available -#}\n{%- if tools -%}\n {{- '\\n\\n' ~ '# Tools' ~ '\\n' ~ 'You may call one or more tools to assist with the user query.\\nHere are the tools available in JSONSchema format:' ~ '\\n' }}\n {{- '\\n' ~ '<tools>' ~ '\\n' }}\n {{- render_tool_namespace(\"functions\", tools) }}\n {{- '</tools>' ~ '\\n\\n' }}\n{{- 'When making tool calls, use XML format to invoke tools and pass parameters:' ~ '\\n' }}\n{{- '\\n' ~ toolcall_begin_token }}\n<invoke name=\"tool-name-1\">\n<parameter name=\"param-key-1\">param-value-1</parameter>\n<parameter name=\"param-key-2\">param-value-2</parameter>\n...\n</invoke>\n{{- '\\n' ~ toolcall_end_token }}\n{%- endif -%}\n{{- '[e~[\\n' }}\n\n{#- Render messages -#}\n{%- set last_tool_call = namespace(name=none) -%}\n{%- for message in conversation_messages -%}\n {%- if message.role == 'assistant' -%}\n {#- Only render reasoning_content if no user message follows -#}\n {{- ']~b]ai' ~ '\\n' }}\n\n {%- set reasoning_content = '' %}\n {%- set content = visible_text(message.content) %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].strip('\\n').split('<think>')[-1].strip('\\n') %}\n {%- set content = content.split('</think>')[-1].strip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if reasoning_content and loop.index0 > ns.last_user_index -%}\n {{- '<think>' ~ '\\n' ~ reasoning_content ~ '\\n' ~ '</think>' ~ '\\n\\n' }}\n {%- endif -%}\n {%- if content -%}\n {{- content }}\n {%- endif -%}\n {%- if message.tool_calls -%}\n {{- '\\n' ~ toolcall_begin_token ~ '\\n' }}\n\n {%- for tool_call in message.tool_calls -%}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<invoke name=\"' + tool_call.name + '\">' }}\n {% set _args = tool_call.arguments %}\n {%- for k, v in _args.items() %}\n {{- '<parameter name=\"' + k + '\">' }}\n {{- v | tojson(ensure_ascii=False) if v is not string else v }}\n {{- '</parameter>' }}\n {% endfor %}\n {{- '</invoke>' ~ '\\n' }}\n {%- endfor -%}\n \n {{- toolcall_end_token}}\n {%- set last_tool_call.name = message.tool_calls[-1].name -%}\n {%- else -%}\n {%- set last_tool_call.name = none -%}\n {%- endif -%}\n {{- '[e~[' ~ '\\n' }}\n \n {%- elif message.role == 'tool' -%}\n {%- if last_tool_call.name is none -%}\n {{- raise_exception(\"Message has tool role, but there was no previous assistant message with a tool call!\") }}\n {%- endif -%}\n {%- if loop.first or (conversation_messages[loop.index0 - 1].role != 'tool') -%}\n {{- ']~b]tool' }}\n {%- endif -%}\n {%- if message.content is string -%}\n {{- '\\n<response>' }}\n {{- message.content }}\n {{- '</response>' }}\n {%- else -%}\n {%- for tr in message.content -%}\n {{- '\\n<response>' }}\n {{- tr.output if tr.output is defined else (tr.text if tr.type == 'text' and tr.text is defined else tr) }}\n {{- '\\n</response>' }}\n {%- endfor -%}\n {%- endif -%}\n {%- if loop.last or (conversation_messages[loop.index0 + 1].role != 'tool') -%}\n {{- '[e~[\\n' -}}\n {%- endif -%}\n \n {%- elif message.role == 'user' -%}\n {{- ']~b]user' ~ '\\n' }}\n {{- visible_text(message.content) }}\n {{- '[e~[' ~ '\\n' }}\n {%- endif -%}\n{%- endfor -%}\n\n{#- Generation prompt -#}\n{%- if add_generation_prompt -%}\n{{- ']~b]ai' ~ '\\n' ~ '<think>' ~ '\\n' }}\n{%- endif -%}\n\n{# Copyright 2025-present Unsloth. Apache 2.0 License. #}"
500
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff