From e5c98976c22b155954a525a8b04e7c61e6ba8cf0 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Wed, 18 Sep 2024 11:18:28 +0800 Subject: [PATCH] update tokenizer_config --- .gitattributes | 13 +------------ tokenizer_config.json | 4 ++-- 2 files changed, 3 insertions(+), 14 deletions(-) diff --git a/.gitattributes b/.gitattributes index 8984f08..39e7ae7 100644 --- a/.gitattributes +++ b/.gitattributes @@ -32,15 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text -*tfevents* filter=lfs diff=lfs merge=lfs -text -model-00001-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00002-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00003-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00004-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00005-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00006-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00007-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00008-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00009-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00010-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text -model-00011-of-00011.safetensors filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/tokenizer_config.json b/tokenizer_config.json index ea25edd..1cad147 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -195,7 +195,7 @@ "<|video_pad|>" ], "bos_token": null, - "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\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 XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{{\\\"name\\\": , \\\"arguments\\\": }}\\n<|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 Qwen, created by Alibaba Cloud. You are a helpful assistant.<|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\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\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\\n' }}\n {{- message.content }}\n {{- '\\n' }}\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' }}\n{%- endif %}\n", "clean_up_tokenization_spaces": false, "eos_token": "<|im_end|>", "errors": "replace", @@ -204,4 +204,4 @@ "split_special_tokens": false, "tokenizer_class": "Qwen2Tokenizer", "unk_token": null -} +} \ No newline at end of file