mindfossil commited on
Commit
bf53e06
·
verified ·
1 Parent(s): 93f3044

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (4) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +44 -77
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +188 -12
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja CHANGED
@@ -1,87 +1,54 @@
1
- {%- if messages[0]["role"] == "system" %}
2
- {%- set system_message = messages[0]["content"] %}
3
- {%- set loop_messages = messages[1:] %}
 
 
 
 
 
 
 
 
 
 
4
  {%- else %}
5
- {%- set loop_messages = messages %}
6
- {%- endif %}
7
- {%- if not tools is defined %}
8
- {%- set tools = none %}
9
- {%- endif %}
10
- {%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
11
-
12
- {#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
13
- {%- set ns = namespace() %}
14
- {%- set ns.index = 0 %}
15
- {%- for message in loop_messages %}
16
- {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
17
- {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
18
- {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
19
- {%- endif %}
20
- {%- set ns.index = ns.index + 1 %}
21
  {%- endif %}
22
- {%- endfor %}
23
-
24
- {{- bos_token }}
25
- {%- for message in loop_messages %}
26
- {%- if message["role"] == "user" %}
27
- {%- if tools is not none and (message == user_messages[-1]) %}
28
- {{- "[AVAILABLE_TOOLS] [" }}
29
- {%- for tool in tools %}
30
- {%- set tool = tool.function %}
31
- {{- '{"type": "function", "function": {' }}
32
- {%- for key, val in tool.items() if key != "return" %}
33
- {%- if val is string %}
34
- {{- '"' + key + '": "' + val + '"' }}
35
- {%- else %}
36
- {{- '"' + key + '": ' + val|tojson }}
37
- {%- endif %}
38
- {%- if not loop.last %}
39
- {{- ", " }}
40
- {%- endif %}
41
- {%- endfor %}
42
- {{- "}}" }}
43
- {%- if not loop.last %}
44
- {{- ", " }}
45
- {%- else %}
46
- {{- "]" }}
47
- {%- endif %}
48
- {%- endfor %}
49
- {{- "[/AVAILABLE_TOOLS]" }}
50
- {%- endif %}
51
- {%- if loop.last and system_message is defined %}
52
- {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
53
- {%- else %}
54
- {{- "[INST] " + message["content"] + "[/INST]" }}
55
  {%- endif %}
56
- {%- elif message.tool_calls is defined and message.tool_calls is not none %}
57
- {{- "[TOOL_CALLS] [" }}
58
  {%- for tool_call in message.tool_calls %}
59
- {%- set out = tool_call.function|tojson %}
60
- {{- out[:-1] }}
61
- {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
62
- {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
63
- {%- endif %}
64
- {{- ', "id": "' + tool_call.id + '"}' }}
65
- {%- if not loop.last %}
66
- {{- ", " }}
67
- {%- else %}
68
- {{- "]" + eos_token }}
69
  {%- endif %}
 
 
 
 
 
70
  {%- endfor %}
71
- {%- elif message["role"] == "assistant" %}
72
- {{- " " + message["content"]|trim + eos_token}}
73
- {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
74
- {%- if message.content is defined and message.content.content is defined %}
75
- {%- set content = message.content.content %}
76
- {%- else %}
77
- {%- set content = message.content %}
78
  {%- endif %}
79
- {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
80
- {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
81
- {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
 
 
82
  {%- endif %}
83
- {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
84
- {%- else %}
85
- {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
86
  {%- endif %}
87
  {%- endfor %}
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# 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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
  {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
 
 
 
 
 
 
 
 
 
 
 
 
19
  {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  {%- endif %}
 
 
29
  {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
 
 
 
 
 
 
 
 
32
  {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
  {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
 
 
 
43
  {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
  {%- endif %}
 
 
 
50
  {%- endif %}
51
  {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,17 +1,193 @@
1
  {
2
- "add_prefix_space": true,
3
  "backend": "tokenizers",
4
- "bos_token": "<s>",
5
  "clean_up_tokenization_spaces": false,
6
- "eos_token": "</s>",
 
7
  "is_local": false,
8
- "legacy": false,
9
- "local_files_only": false,
10
- "model_max_length": 1000000000000000019884624838656,
11
- "pad_token": null,
12
- "sp_model_kwargs": {},
13
- "spaces_between_special_tokens": false,
14
- "tokenizer_class": "TokenizersBackend",
15
- "unk_token": "<unk>",
16
- "use_default_system_prompt": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "backend": "tokenizers",
4
+ "bos_token": null,
5
  "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
  "is_local": false,
9
+ "model_max_length": 32768,
10
+ "pad_token": "<|vision_pad|>",
11
+ "padding_side": "left",
12
+ "split_special_tokens": false,
13
+ "tokenizer_class": "Qwen2Tokenizer",
14
+ "unk_token": null,
15
+ "added_tokens_decoder": {
16
+ "151643": {
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ "151644": {
25
+ "content": "<|im_start|>",
26
+ "single_word": false,
27
+ "lstrip": false,
28
+ "rstrip": false,
29
+ "normalized": false,
30
+ "special": true
31
+ },
32
+ "151645": {
33
+ "content": "<|im_end|>",
34
+ "single_word": false,
35
+ "lstrip": false,
36
+ "rstrip": false,
37
+ "normalized": false,
38
+ "special": true
39
+ },
40
+ "151646": {
41
+ "content": "<|object_ref_start|>",
42
+ "single_word": false,
43
+ "lstrip": false,
44
+ "rstrip": false,
45
+ "normalized": false,
46
+ "special": true
47
+ },
48
+ "151647": {
49
+ "content": "<|object_ref_end|>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ "151648": {
57
+ "content": "<|box_start|>",
58
+ "single_word": false,
59
+ "lstrip": false,
60
+ "rstrip": false,
61
+ "normalized": false,
62
+ "special": true
63
+ },
64
+ "151649": {
65
+ "content": "<|box_end|>",
66
+ "single_word": false,
67
+ "lstrip": false,
68
+ "rstrip": false,
69
+ "normalized": false,
70
+ "special": true
71
+ },
72
+ "151650": {
73
+ "content": "<|quad_start|>",
74
+ "single_word": false,
75
+ "lstrip": false,
76
+ "rstrip": false,
77
+ "normalized": false,
78
+ "special": true
79
+ },
80
+ "151651": {
81
+ "content": "<|quad_end|>",
82
+ "single_word": false,
83
+ "lstrip": false,
84
+ "rstrip": false,
85
+ "normalized": false,
86
+ "special": true
87
+ },
88
+ "151652": {
89
+ "content": "<|vision_start|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ "151653": {
97
+ "content": "<|vision_end|>",
98
+ "single_word": false,
99
+ "lstrip": false,
100
+ "rstrip": false,
101
+ "normalized": false,
102
+ "special": true
103
+ },
104
+ "151654": {
105
+ "content": "<|vision_pad|>",
106
+ "single_word": false,
107
+ "lstrip": false,
108
+ "rstrip": false,
109
+ "normalized": false,
110
+ "special": true
111
+ },
112
+ "151655": {
113
+ "content": "<|image_pad|>",
114
+ "single_word": false,
115
+ "lstrip": false,
116
+ "rstrip": false,
117
+ "normalized": false,
118
+ "special": true
119
+ },
120
+ "151656": {
121
+ "content": "<|video_pad|>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": false,
126
+ "special": true
127
+ },
128
+ "151657": {
129
+ "content": "<tool_call>",
130
+ "single_word": false,
131
+ "lstrip": false,
132
+ "rstrip": false,
133
+ "normalized": false,
134
+ "special": false
135
+ },
136
+ "151658": {
137
+ "content": "</tool_call>",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": false,
142
+ "special": false
143
+ },
144
+ "151659": {
145
+ "content": "<|fim_prefix|>",
146
+ "single_word": false,
147
+ "lstrip": false,
148
+ "rstrip": false,
149
+ "normalized": false,
150
+ "special": false
151
+ },
152
+ "151660": {
153
+ "content": "<|fim_middle|>",
154
+ "single_word": false,
155
+ "lstrip": false,
156
+ "rstrip": false,
157
+ "normalized": false,
158
+ "special": false
159
+ },
160
+ "151661": {
161
+ "content": "<|fim_suffix|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": false
167
+ },
168
+ "151662": {
169
+ "content": "<|fim_pad|>",
170
+ "single_word": false,
171
+ "lstrip": false,
172
+ "rstrip": false,
173
+ "normalized": false,
174
+ "special": false
175
+ },
176
+ "151663": {
177
+ "content": "<|repo_name|>",
178
+ "single_word": false,
179
+ "lstrip": false,
180
+ "rstrip": false,
181
+ "normalized": false,
182
+ "special": false
183
+ },
184
+ "151664": {
185
+ "content": "<|file_sep|>",
186
+ "single_word": false,
187
+ "lstrip": false,
188
+ "rstrip": false,
189
+ "normalized": false,
190
+ "special": false
191
+ }
192
+ }
193
  }