Upload tokenizer
Browse files- chat_template.jinja +4 -54
- special_tokens_map.json +2 -14
- tokenizer_config.json +3 -4
chat_template.jinja
CHANGED
|
@@ -1,54 +1,4 @@
|
|
| 1 |
-
{
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
|
| 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 %}
|
|
|
|
| 1 |
+
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages %}{% else %}{% set loop_messages = [{'role': 'system', 'content': 'You are an expert programmer and unit test generator. Your goal is to write a comprehensive and correct unit test code for the given source code based on the instruction.'}] + messages %}{% endif %}{% for message in loop_messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
+
' + message['content'] + '<|im_end|>' + '
|
| 3 |
+
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
+
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
special_tokens_map.json
CHANGED
|
@@ -14,18 +14,6 @@
|
|
| 14 |
"<|image_pad|>",
|
| 15 |
"<|video_pad|>"
|
| 16 |
],
|
| 17 |
-
"eos_token":
|
| 18 |
-
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
"pad_token": {
|
| 25 |
-
"content": "<|PAD_TOKEN|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
}
|
|
|
|
| 14 |
"<|image_pad|>",
|
| 15 |
"<|video_pad|>"
|
| 16 |
],
|
| 17 |
+
"eos_token": "<|im_end|>",
|
| 18 |
+
"pad_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
}
|
tokenizer_config.json
CHANGED
|
@@ -208,10 +208,9 @@
|
|
| 208 |
"errors": "replace",
|
| 209 |
"extra_special_tokens": {},
|
| 210 |
"model_max_length": 32768,
|
| 211 |
-
"pad_token": "<|
|
| 212 |
"padding_side": "right",
|
| 213 |
"split_special_tokens": false,
|
| 214 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 215 |
-
"unk_token": null
|
| 216 |
-
|
| 217 |
-
}
|
|
|
|
| 208 |
"errors": "replace",
|
| 209 |
"extra_special_tokens": {},
|
| 210 |
"model_max_length": 32768,
|
| 211 |
+
"pad_token": "<|endoftext|>",
|
| 212 |
"padding_side": "right",
|
| 213 |
"split_special_tokens": false,
|
| 214 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 215 |
+
"unk_token": null
|
| 216 |
+
}
|
|
|