Hugging Face's logo

ZygAI
/
ZygAI-OSS-Translate-Lithuanian

Translation
Transformers
Safetensors
PEFT
English
Lithuanian
lithuanian
english-to-lithuanian
trl
sft
lora
zygai
Model card Files
xet
 Community
ZygAI commited on
Commit
ffff090
·
verified ·
1 Parent(s): 2dbcd75

Upload tokenizer

Browse files
Files changed (3) hide show
  1. chat_template.jinja +179 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +17 -0
chat_template.jinja ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token }}{%- if tools %}
2
+ {%- set tool_definitions %}
3
+ {{- "# Tools\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
4
+ {%- for tool in tools %}
5
+ {{- "\n" }}
6
+ {{- tool | tojson(ensure_ascii=False) }}
7
+ {%- endfor %}
8
+ {{- '\n</tools>\n\nTool usage guidelines:\n- You may call zero or more functions. If no function calls are needed, just answer normally and do not include any <function ... </function>.\n- When calling a function, return an XML object within <function ... </function> using:\n<function name="function-name"><param name="param-name">param-value</param></function>\n- param-value may be multi-line. If it contains <, & or newline characters, wrap it in a CDATA block: <param name="param-name"><![CDATA[...multi-line value...]]></param>' }}
9
+ {%- endset %}
10
+
11
+ {{- '<|im_start|>system\n' }}
12
+ {%- if messages[0].role == 'system' %}
13
+ {%- if '<tool_def_sep>' in messages[0].content %}
14
+ {{- messages[0].content.replace('<tool_def_sep>', tool_definitions) }}
15
+ {%- else %}
16
+ {{- messages[0].content + '\n\n' + tool_definitions }}
17
+ {%- endif %}
18
+ {%- else %}
19
+ {{- tool_definitions.lstrip() }}
20
+ {%- endif %}
21
+ {{- '<|im_end|>\n' }}
22
+ {%- else %}
23
+ {%- if messages[0].role == 'system' %}
24
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
25
+ {%- endif %}
26
+ {%- endif %}
27
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
28
+ {%- for message in messages[::-1] %}
29
+ {%- set index = (messages|length - 1) - loop.index0 %}
30
+ {%- 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>')) %}
31
+ {%- set ns.multi_step_tool = false %}
32
+ {%- set ns.last_query_index = index %}
33
+ {%- endif %}
34
+ {%- endfor %}
35
+ {%- for message in messages %}
36
+ {%- if message.content is string %}
37
+ {%- set content = message.content %}
38
+ {%- else %}
39
+ {%- set content = '' %}
40
+ {%- endif %}
41
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
42
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
43
+ {%- elif message.role == "assistant" %}
44
+ {%- set reasoning_content = '' %}
45
+ {%- if message.reasoning_content is string %}
46
+ {%- set reasoning_content = message.reasoning_content %}
47
+ {%- else %}
48
+ {%- if '</think>' in content %}
49
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
50
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
51
+ {%- endif %}
52
+ {%- endif %}
53
+
54
+ {%- if message.tool_calls %}
55
+ {%- set content_parts = content.split('<tool_sep>') %}
56
+ {%- set processed_content = content_parts[0] %}
57
+ {%- set tool_calls_count = message.tool_calls|length %}
58
+ {%- set tool_sep_count = content_parts|length - 1 %}
59
+ {%- set min_count = [tool_calls_count, tool_sep_count]|min %}
60
+
61
+ {%- for i in range(1, content_parts|length) %}
62
+ {%- set tool_index = i - 1 %}
63
+ {%- if tool_index < tool_calls_count %}
64
+ {%- set tool_call = message.tool_calls[tool_index] %}
65
+ {%- if tool_call.function %}
66
+ {%- set tool_call = tool_call.function %}
67
+ {%- endif %}
68
+ {%- set single_tool_xml %}
69
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
70
+ {%- if tool_call.arguments %}
71
+ {%- set args_dict = tool_call.arguments %}
72
+ {%- for param_name, param_value in args_dict.items() %}
73
+ {{- '<param name="' ~ param_name ~ '">' }}
74
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
75
+ {{- '<![CDATA[' + param_value + ']]>' }}
76
+ {%- else %}
77
+ {{- param_value }}
78
+ {%- endif %}
79
+ {{- '</param>' }}
80
+ {%- endfor %}
81
+ {%- endif %}
82
+ {{- '</function>' }}
83
+ {%- endset %}
84
+ {%- set processed_content = processed_content + single_tool_xml + content_parts[i] %}
85
+ {%- else %}
86
+ {%- set processed_content = processed_content + content_parts[i] %}
87
+ {%- endif %}
88
+ {%- endfor %}
89
+
90
+ {%- if tool_calls_count > tool_sep_count %}
91
+ {%- for remaining_index in range(tool_sep_count, tool_calls_count) %}
92
+ {%- set tool_call = message.tool_calls[remaining_index] %}
93
+ {%- if tool_call.function %}
94
+ {%- set tool_call = tool_call.function %}
95
+ {%- endif %}
96
+ {%- set remaining_tool_xml %}
97
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
98
+ {%- if tool_call.arguments %}
99
+ {%- set args_dict = tool_call.arguments %}
100
+ {%- for param_name, param_value in args_dict.items() %}
101
+ {{- '<param name="' ~ param_name ~ '">' }}
102
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
103
+ {{- '<![CDATA[' + param_value + ']]>' }}
104
+ {%- else %}
105
+ {{- param_value }}
106
+ {%- endif %}
107
+ {{- '</param>' }}
108
+ {%- endfor %}
109
+ {%- endif %}
110
+ {{- '</function>' }}
111
+ {%- endset %}
112
+ {%- set processed_content = processed_content + remaining_tool_xml %}
113
+ {%- endfor %}
114
+ {%- endif %}
115
+
116
+ {%- set content = processed_content %}
117
+ {%- endif %}
118
+
119
+ {%- if loop.index0 > ns.last_query_index %}
120
+ {%- if reasoning_content %}
121
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
122
+ {%- else %}
123
+ {{- '<|im_start|>' + message.role + '\n' + content }}
124
+ {%- endif %}
125
+ {%- else %}
126
+ {{- '<|im_start|>' + message.role + '\n' + content }}
127
+ {%- endif %}
128
+
129
+ {%- if message.tool_calls and not has_tool_sep %}
130
+ {%- for tool_call in message.tool_calls %}
131
+ {%- if (loop.first and content) or (not loop.first) %}
132
+ {{- '\n' }}
133
+ {%- endif %}
134
+ {%- if tool_call.function %}
135
+ {%- set tool_call = tool_call.function %}
136
+ {%- endif %}
137
+ {{- '<function name="' ~ tool_call.name ~ '">' }}
138
+ {%- if tool_call.arguments %}
139
+ {%- set args_dict = tool_call.arguments %}
140
+ {%- for param_name, param_value in args_dict.items() %}
141
+ {{- '<param name="' ~ param_name ~ '">' }}
142
+ {%- if param_value is string and ('<' in param_value or '&' in param_value or '\n' in param_value) %}
143
+ {{- '<![CDATA[' + param_value + ']]>' }}
144
+ {%- else %}
145
+ {{- param_value }}
146
+ {%- endif %}
147
+ {{- '</param>' }}
148
+ {%- endfor %}
149
+ {%- endif %}
150
+ {{- '</function>' }}
151
+ {%- endfor %}
152
+ {%- endif %}
153
+ {{- '<|im_end|>\n' }}
154
+ {%- elif message.role == "tool" %}
155
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
156
+ {{- '<|im_start|>user' }}
157
+ {%- endif %}
158
+ {{- '\n<tool_response>\n' }}
159
+ {%- if message.content is string %}
160
+ {{- content }}
161
+ {%- else %}
162
+ {{- message.content | tojson(ensure_ascii=False) }}
163
+ {%- endif %}
164
+ {{- '\n</tool_response>' }}
165
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
166
+ {{- '<|im_end|>\n' }}
167
+ {%- endif %}
168
+ {%- endif %}
169
+ {%- endfor %}
170
+ {%- if add_generation_prompt %}
171
+ {{- '<|im_start|>assistant\n' }}
172
+ {%- if enable_thinking is defined %}
173
+ {%- if enable_thinking is false %}
174
+ {{- '<think>\n\n</think>\n\n' }}
175
+ {%- elif enable_thinking is true %}
176
+ {{- '<think>\n' }}
177
+ {%- endif %}
178
+ {%- endif %}
179
+ {%- endif %}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<s>",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "is_local": false,
8
+ "legacy": true,
9
+ "local_files_only": false,
10
+ "model_max_length": 1000000000000000019884624838656,
11
+ "pad_token": "</s>",
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
+ }