Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
3 |
+
size 11421896
|
tokenizer_config.json
CHANGED
@@ -195,14 +195,13 @@
|
|
195 |
"<|video_pad|>"
|
196 |
],
|
197 |
"bos_token": null,
|
198 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
202 |
"extra_special_tokens": {},
|
203 |
"model_max_length": 131072,
|
204 |
"pad_token": "<|endoftext|>",
|
205 |
-
"padding_side": "left",
|
206 |
"split_special_tokens": false,
|
207 |
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
"unk_token": null
|
|
|
195 |
"<|video_pad|>"
|
196 |
],
|
197 |
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant. You first think through requests step-by-step in your mind and then provide the user with the answer.\n\nYou put your thoughts within <think>...</think> tags and provide your answer within <answer>...</answer> tags.\n' }}\n {%- endif %}\n {{- \"\\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>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant. You first think through requests step-by-step in your mind and then provide the user with the answer.\n\nYou put your thoughts within <think>...</think> tags and provide your answer within <answer>...</answer> tags.\n<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n<think>\\n' }}\n{%- endif %}\n",
|
199 |
"clean_up_tokenization_spaces": false,
|
200 |
"eos_token": "<|im_end|>",
|
201 |
"errors": "replace",
|
202 |
"extra_special_tokens": {},
|
203 |
"model_max_length": 131072,
|
204 |
"pad_token": "<|endoftext|>",
|
|
|
205 |
"split_special_tokens": false,
|
206 |
"tokenizer_class": "Qwen2Tokenizer",
|
207 |
"unk_token": null
|