From abbf036e5baa1e1fbbc6b31f145039f4e78c6660 Mon Sep 17 00:00:00 2001 From: liukuikun <24622904+Harold-lkk@users.noreply.github.com> Date: Fri, 19 Jan 2024 20:02:48 +0800 Subject: [PATCH] [Enchance] update chat format (#634) --- chat/chat_format.md | 166 +++++++++++++++++++------------------- chat/chat_format_zh-CN.md | 166 +++++++++++++++++++------------------- chat/web_demo.py | 8 +- 3 files changed, 170 insertions(+), 170 deletions(-) diff --git a/chat/chat_format.md b/chat/chat_format.md index eaee8b7..303d99d 100644 --- a/chat/chat_format.md +++ b/chat/chat_format.md @@ -9,24 +9,24 @@ InternLM2-Chat adopts a new chat format to flexibly support a wider range of app The regular chat structure usually contains three roles: `system`, `user`, and `assistant`, formatted as follows for multi-turn dialogues: ``` -[UNUSED_TOKEN_146]system -You are InternLM2-Chat, a harmless AI assistant[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -Hello[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -Hello, I am InternLM2-Chat, how can I assist you?[UNUSED_TOKEN_145] +<|im_start|>system +You are InternLM2-Chat, a harmless AI assistant<|im_end|> +<|im_start|>user +Hello<|im_end|> +<|im_start|>assistant +Hello, I am InternLM2-Chat, how can I assist you?<|im_end|> ``` -Here, `[UNUSED_TOKEN_146]` acts as the start token for each turn of dialogue, and `[UNUSED_TOKEN_145]` as the end token. Each turn of dialogue typically starts with `[UNUSED_TOKEN_146]role` and ends with the model's output `[UNUSED_TOKEN_145]`, where role represents `system`, `user`, `assistant`, and `environment`. You may refer to the [code in huggingface](https://huggingface.co/internlm/internlm2-chat-7b/blob/main/modeling_internlm2.py#L1138) to see how the chat history is organized. +Here, `<|im_start|>` acts as the start token for each turn of dialogue, and `<|im_end|>` as the end token. Each turn of dialogue typically starts with `<|im_start|>role` and ends with the model's output `<|im_end|>`, where role represents `system`, `user`, `assistant`, and `environment`. You may refer to the [code in huggingface](https://huggingface.co/internlm/internlm2-chat-7b/blob/main/modeling_internlm2.py#L1138) to see how the chat history is organized. Currently, the InternLM2-Chat model's vocabulary maintains the following mappings to support full functionalities: -- `[UNUSED_TOKEN_146]`: Start token for each role's dialogue, the token ID is **92543** -- `[UNUSED_TOKEN_145]`: End token for each role's dialogue, the token ID is **92542** -- `[UNUSED_TOKEN_144]`: Start token for invoking external plugins, the token ID is **92541** -- `[UNUSED_TOKEN_143]`: End token for invoking external plugins, the token ID is **92540** -- `[UNUSED_TOKEN_142]`: Code interpreter, the token ID is **92539** -- `[UNUSED_TOKEN_141]`: External plugins, regular tools, the token ID is **92538** +- `<|im_start|>`: Start token for each role's dialogue, the token ID is **92543** +- `<|im_end|>`: End token for each role's dialogue, the token ID is **92542** +- `<|action_start|>`: Start token for invoking external tools, like interpreter or plugin, the token ID is **92541** +- `<|action_end|>`: End token for invoking external plugins, the token ID is **92540** +- `<|interpreter|>`: Code interpreter, the token ID is **92539** +- `<|plugin|>`: External plugins, regular tools, the token ID is **92538** ## Complete Structure @@ -37,9 +37,9 @@ The complete chat format of InternLM2-Chat, based on the basic structure, also i InternLM2-Chat support multiple formats (e.g., ReAct) to conduct function call, especially **json format** to ease downstream applications。An example of complete function call is shown below. ``` -[UNUSED_TOKEN_146]system -You are InternLM2-Chat, a harmless AI assistant[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_141] +<|im_start|>system +You are InternLM2-Chat, a harmless AI assistant<|im_end|> +<|im_start|>system name=<|plugin|> [ { "name": "get_current_weather", @@ -57,46 +57,46 @@ You are InternLM2-Chat, a harmless AI assistant[UNUSED_TOKEN_145] }, } ] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -I want to know today's weather in Shanghai[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -Sure, I will search for the weather of Shanghai.[UNUSED_TOKEN_144][UNUSED_TOKEN_141] -{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}[UNUSED_TOKEN_143][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_141] -{"temperature": 22}[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -The weather in Shanghai is 22 celsius[UNUSED_TOKEN_145] +<|im_end|> +<|im_start|>user +I want to know today's weather in Shanghai<|im_end|> +<|im_start|>assistant +Sure, I will search for the weather of Shanghai.<|action_start|><|plugin|> +{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}<|action_end|><|im_end|> +<|im_start|>environment name=<|plugin|> +{"temperature": 22}<|im_end|> +<|im_start|>assistant +The weather in Shanghai is 22 celsius<|im_end|> ``` -1. First，there will be a new system prompt that describe the protocol of tools in json format. The content starts with `[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_141]\n` and ends with `[UNUSED_TOKEN_145]`. `name=[UNUSED_TOKEN_141]` indicates the system prompt comes from tools. InternLM2-Chat supports and follows multiple system prompts in the chat history, so we can also see the system prompt ask the model to be helpful assistant. -2. Model will call the tools in a streaming format after receving the user prompt, i.e., it will naturally speak something (thoughts, helpful response) then call the tools. The model will output `[UNUSED_TOKEN_144][UNUSED_TOKEN_141]`, where `[UNUSED_TOKEN_144]` indicates the model needs to call extensions and `[UNUSED_TOKEN_141]` indicates it want to use common tools. Then the model will output the calling parameters in json format and end it with `[UNUSED_TOKEN_143]`. -3. The environment returns the function calling outputs, starts with `[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_141]`, indicating it comes from the function calling in the environment. The content is in json format, `{"temperature": 22}`, ends with `[UNUSED_TOKEN_145]`. +1. First，there will be a new system prompt that describe the protocol of tools in json format. The content starts with `<|im_start|>system name=<|plugin|>\n` and ends with `<|im_end|>`. `name=<|plugin|>` indicates the system prompt comes from tools. InternLM2-Chat supports and follows multiple system prompts in the chat history, so we can also see the system prompt ask the model to be helpful assistant. +2. Model will call the tools in a streaming format after receving the user prompt, i.e., it will naturally speak something (thoughts, helpful response) then call the tools. The model will output `<|action_start|><|plugin|>`, where `<|action_start|>` indicates the model needs to call extensions and `<|plugin|>` indicates it want to use common tools. Then the model will output the calling parameters in json format and end it with `<|action_end|>`. +3. The environment returns the function calling outputs, starts with `<|im_start|>environment name=<|plugin|>`, indicating it comes from the function calling in the environment. The content is in json format, `{"temperature": 22}`, ends with `<|im_end|>`. ### Code Interpreter InternLM2-Chat support to use code interpreter to solve complex math problems and data analysis. The whole process is similar to the function calling, shown as below. ``` -[UNUSED_TOKEN_146]system -You are InternLM2-Chat, a harmless AI assistant[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_142] +<|im_start|>system +You are InternLM2-Chat, a harmless AI assistant<|im_end|> +<|im_start|>system name=<|interpreter|> You now have access to a Jupyter notebook environment supporting Python code execution. Just send code to python to run in this stateful environment. This feature is suitable for: - Data analysis or processing (such as data manipulation and graphic creation) - Complex calculations (such as math and physics problems) - Programming examples (for understanding programming concepts or language features) - Text processing and analysis (including text analysis and natural language processing) - Machine learning and data science (model training and data visualization) -- File operations and data import (handling CSV, JSON, etc. formats)[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user +- File operations and data import (handling CSV, JSON, etc. formats)<|im_end|> +<|im_start|>user Please help me process and visualize this dataset. -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user name=file -[{"path": "data.csv", size='10K'}][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>user name=file +[{"path": "data.csv", size='10K'}]<|im_end|> +<|im_start|>assistant I have processed the data and visualized it for you. -[UNUSED_TOKEN_144][UNUSED_TOKEN_142] +<|action_start|><|interpreter|> ```python import plotly.express as px import pandas as pd @@ -118,40 +118,40 @@ fig.update_traces(hovertemplate='Date: %{text}
Wind Direction 9am: %{x # Show the plot fig.show() -```[UNUSED_TOKEN_143] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_142] +```<|action_end|> +<|im_end|> +<|im_start|>environment name=<|interpreter|> ![image](xxx.png) -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -Since the code output is not included here, I cannot provide specific chart content. However, if the code executed correctly, it should display a polar plot with two filled areas representing the relationship between wind direction at 9 am and rainfall, and between wind direction at 3 pm and rainfall, respectively. The values for each direction are based on the average rainfall calculated from the provided dataset. The chart should have a clear title, a legend, and be intuitive for comparing rainfall with different wind directions. Given the use of a dark theme, the overall appearance of the chart should be bright lines and filled areas on a dark background.[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -Can you explain the code?[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>assistant +Since the code output is not included here, I cannot provide specific chart content. However, if the code executed correctly, it should display a polar plot with two filled areas representing the relationship between wind direction at 9 am and rainfall, and between wind direction at 3 pm and rainfall, respectively. The values for each direction are based on the average rainfall calculated from the provided dataset. The chart should have a clear title, a legend, and be intuitive for comparing rainfall with different wind directions. Given the use of a dark theme, the overall appearance of the chart should be bright lines and filled areas on a dark background.<|im_end|> +<|im_start|>user +Can you explain the code?<|im_end|> +<|im_start|>assistant The code uses Python's Plotly library to create a polar plot that shows the relationship between wind direction and rainfall. It starts by creating a Plotly Figure object. Then, I added two `Scatterpolar` traces. The first trace shows the relationship between wind direction at 9 am and average rainfall, and the second trace shows the same for 3 pm. In these traces, the `r` parameter represents the average rainfall, and `theta` represents the wind direction. `fill='toself'` means the shape is filled to its own boundary. Next, I updated the chart layout, hid the radial axis, added a legend, set the title and its font, chose a dark theme, and set the chart's background color, width, and height. Finally, the chart was displayed using `fig.show()`. -[UNUSED_TOKEN_145] +<|im_end|> ``` -1. First，there will be a new system prompt that describe the usages of code interpreter. The content starts with `[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_142]\n` and ends with `[UNUSED_TOKEN_145]`. `name=[UNUSED_TOKEN_142]` indicates the system prompt comes from code interpreter. InternLM2-Chat supports and follows multiple system prompts in the chat history, so we can also see the system prompt ask the model to be helpful assistant. -2. Model will call the tools in a streaming format after receving the user prompt, i.e., it will naturally speak something (thoughts, helpful response) then call the code interpreter. The model will output `[UNUSED_TOKEN_144][UNUSED_TOKEN_142]`, where `[UNUSED_TOKEN_144]` indicates the model needs to call extensions and `[UNUSED_TOKEN_142]` indicates it want to use code interpreter. Then the model will output the code in a markdown-style code block and end it with `[UNUSED_TOKEN_143]`. -3. The environment will execute the code and return outputs, starts with `[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_142]`, indicating it comes from the code interpreter in the environment, and the content ends with `[UNUSED_TOKEN_145]`. +1. First，there will be a new system prompt that describe the usages of code interpreter. The content starts with `<|im_start|>system name=<|interpreter|>\n` and ends with `<|im_end|>`. `name=<|interpreter|>` indicates the system prompt comes from code interpreter. InternLM2-Chat supports and follows multiple system prompts in the chat history, so we can also see the system prompt ask the model to be helpful assistant. +2. Model will call the tools in a streaming format after receving the user prompt, i.e., it will naturally speak something (thoughts, helpful response) then call the code interpreter. The model will output `<|action_start|><|interpreter|>`, where `<|action_start|>` indicates the model needs to call extensions and `<|interpreter|>` indicates it want to use code interpreter. Then the model will output the code in a markdown-style code block and end it with `<|action_end|>`. +3. The environment will execute the code and return outputs, starts with `<|im_start|>environment name=<|interpreter|>`, indicating it comes from the code interpreter in the environment, and the content ends with `<|im_end|>`. ### Function Call + Code Interpreter InternLM2-Chat can choose to use tools or code interpreter automatically. We only need to send the system prompt of both to the model respectively. An example is shown as below ``` -[UNUSED_TOKEN_146]system -You are InternLM2-Chat, a harmless AI assistant[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_142] +<|im_start|>system +You are InternLM2-Chat, a harmless AI assistant<|im_end|> +<|im_start|>system name=<|interpreter|> You now have access to a Jupyter notebook environment supporting Python code execution. Just send code to python to run in this stateful environment. This feature is suitable for: - Data analysis or processing (such as data manipulation and graphic creation) - Complex calculations (such as math and physics problems) - Programming examples (for understanding programming concepts or language features) - Text processing and analysis (including text analysis and natural language processing) - Machine learning and data science (model training and data visualization) -- File operations and data import (handling CSV, JSON, etc. formats)[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_141] +- File operations and data import (handling CSV, JSON, etc. formats)<|im_end|> +<|im_start|>system name=<|plugin|> [ { "name": "get_current_weather", @@ -169,16 +169,16 @@ You now have access to a Jupyter notebook environment supporting Python code exe }, } ] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user +<|im_end|> +<|im_start|>user Please help me process and visualize this dataset. -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user name=file -[{"path": "data.csv", size='10K'}][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>user name=file +[{"path": "data.csv", size='10K'}]<|im_end|> +<|im_start|>assistant I have processed the data and visualized it for you. -[UNUSED_TOKEN_144][UNUSED_TOKEN_142] +<|action_start|><|interpreter|> ```python import plotly.express as px import pandas as pd @@ -200,25 +200,25 @@ fig.update_traces(hovertemplate='Date: %{text}
Wind Direction 9am: %{x # Show the plot fig.show() -```[UNUSED_TOKEN_143] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_142] +```<|action_end|> +<|im_end|> +<|im_start|>environment name=<|interpreter|> ![image](xxx.png) -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -Since the code output is not included here, I cannot provide specific chart content. However, if the code executed correctly, it should display a polar plot with two filled areas representing the relationship between wind direction at 9 am and rainfall, and between wind direction at 3 pm and rainfall, respectively. The values for each direction are based on the average rainfall calculated from the provided dataset. The chart should have a clear title, a legend, and be intuitive for comparing rainfall with different wind directions. Given the use of a dark theme, the overall appearance of the chart should be bright lines and filled areas on a dark background.[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -Can you explain the code?[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>assistant +Since the code output is not included here, I cannot provide specific chart content. However, if the code executed correctly, it should display a polar plot with two filled areas representing the relationship between wind direction at 9 am and rainfall, and between wind direction at 3 pm and rainfall, respectively. The values for each direction are based on the average rainfall calculated from the provided dataset. The chart should have a clear title, a legend, and be intuitive for comparing rainfall with different wind directions. Given the use of a dark theme, the overall appearance of the chart should be bright lines and filled areas on a dark background.<|im_end|> +<|im_start|>user +Can you explain the code?<|im_end|> +<|im_start|>assistant The code uses Python's Plotly library to create a polar plot that shows the relationship between wind direction and rainfall. It starts by creating a Plotly Figure object. Then, I added two `Scatterpolar` traces. The first trace shows the relationship between wind direction at 9 am and average rainfall, and the second trace shows the same for 3 pm. In these traces, the `r` parameter represents the average rainfall, and `theta` represents the wind direction. `fill='toself'` means the shape is filled to its own boundary. Next, I updated the chart layout, hid the radial axis, added a legend, set the title and its font, chose a dark theme, and set the chart's background color, width, and height. Finally, the chart was displayed using `fig.show()`. -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -I want to know today's weather in Shanghai[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -Sure, I will search for the weather of Shanghai.[UNUSED_TOKEN_144][UNUSED_TOKEN_141] -{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}[UNUSED_TOKEN_143][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_141] -{"temperature": 22}[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -The weather in Shanghai is 22 celsius[UNUSED_TOKEN_145] +<|im_end|> +<|im_start|>user +I want to know today's weather in Shanghai<|im_end|> +<|im_start|>assistant +Sure, I will search for the weather of Shanghai.<|action_start|><|plugin|> +{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}<|action_end|><|im_end|> +<|im_start|>environment name=<|plugin|> +{"temperature": 22}<|im_end|> +<|im_start|>assistant +The weather in Shanghai is 22 celsius<|im_end|> ``` diff --git a/chat/chat_format_zh-CN.md b/chat/chat_format_zh-CN.md index 60dc28f..5852f15 100644 --- a/chat/chat_format_zh-CN.md +++ b/chat/chat_format_zh-CN.md @@ -9,24 +9,24 @@ InternLM2-Chat 采用了全新的对话格式，以灵活地支持工具调用 常规的对话结构一般包含 `system`，`user`，`assistant` 三个角色，采用如下格式进行多轮对话 ``` -[UNUSED_TOKEN_146]system -你是书生浦语2，一个无害的人工智能助手[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -你好呀[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -你好，我是书生浦语，请问有什么可以帮助你的吗[UNUSED_TOKEN_145] +<|im_start|>system +你是书生浦语2，一个无害的人工智能助手<|im_end|> +<|im_start|>user +你好呀<|im_end|> +<|im_start|>assistant +你好，我是书生浦语，请问有什么可以帮助你的吗<|im_end|> ``` -其中 `[UNUSED_TOKEN_146]` 充当了每轮对话开始符，`[UNUSED_TOKEN_145]` 充当了当前轮对话结束符。每轮对话一般以 `[UNUSED_TOKEN_146]role` 开头，以模型输出的 `[UNUSED_TOKEN_145]` 结尾，role 代表 `system`，`user`，`assistant` 和 `environment` 角色。你可以参考[huggingface 上的代码](https://huggingface.co/internlm/internlm2-chat-7b/blob/main/modeling_internlm2.py#L1138)来了解对话历史的拼接。 +其中 `<|im_start|>` 充当了每轮对话开始符，`<|im_end|>` 充当了当前轮对话结束符。每轮对话一般以 `<|im_start|>role` 开头，以模型输出的 `<|im_end|>` 结尾，role 代表 `system`，`user`，`assistant` 和 `environment` 角色。你可以参考[huggingface 上的代码](https://huggingface.co/internlm/internlm2-chat-7b/blob/main/modeling_internlm2.py#L1138)来了解对话历史的拼接。 目前，InternLM2-Chat 模型的词表中还维护了如下映射 -- `[UNUSED_TOKEN_146]`：每个角色对话的开始符，在词表中对应的 token ID 是**92543** -- `[UNUSED_TOKEN_145]`：每个角色对话的结束符，在词表中对应的 token ID 是**92542** -- `[UNUSED_TOKEN_144]`：模型调用外部插件的开始符，在词表中对应的 token ID 是**92541** -- `[UNUSED_TOKEN_143]`：模型调用外部插件的结束符，在词表中对应的 token ID 是**92540** -- `[UNUSED_TOKEN_142]`：代码解释器，在词表中对应的 token ID 是**92539** -- `[UNUSED_TOKEN_141]`：外部插件，常规的 tools，在词表中对应的 token ID 是**92538** +- `<|im_start|>`：每个角色对话的开始符，在词表中对应的 token ID 是**92543** +- `<|im_end|>`：每个角色对话的结束符，在词表中对应的 token ID 是**92542** +- `<|action_start|>`：模型调用外部工具(代码解释器或外部插件)的开始符，在词表中对应的 token ID 是**92541** +- `<|action_end|>`：模型调用外部插件的结束符，在词表中对应的 token ID 是**92540** +- `<|interpreter|>`：代码解释器，在词表中对应的 token ID 是**92539** +- `<|plugin|>`：外部插件，常规的 tools，在词表中对应的 token ID 是**92538** ## 完整结构 @@ -37,9 +37,9 @@ InternLM2-Chat 的完整对话格式在上述基本结构的基础上还包含 InternLM2-Chat 的通用工具调用（function call）支持多种格式，尤其是**json 格式**以便捷下游应用。以此为例，一次完整的工具调用流程如下所示： ``` -[UNUSED_TOKEN_146]system -你是书生浦语2，一个无害的人工智能助手[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_141] +<|im_start|>system +你是书生浦语2，一个无害的人工智能助手<|im_end|> +<|im_start|>system name=<|plugin|> [ { "name": "get_current_weather", @@ -57,30 +57,30 @@ InternLM2-Chat 的通用工具调用（function call）支持多种格式，尤 }, } ] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -我想了解今天上海的天气[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -好的，我将为你查询上海的天气。[UNUSED_TOKEN_144][UNUSED_TOKEN_141] -{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}[UNUSED_TOKEN_143][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_141] -{"temperature": 22}[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -上海的天气是 22 摄氏度[UNUSED_TOKEN_145] +<|im_end|> +<|im_start|>user +我想了解今天上海的天气<|im_end|> +<|im_start|>assistant +好的，我将为你查询上海的天气。<|action_start|><|plugin|> +{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}<|action_end|><|im_end|> +<|im_start|>environment name=<|plugin|> +{"temperature": 22}<|im_end|> +<|im_start|>assistant +上海的天气是 22 摄氏度<|im_end|> ``` -1. 首先，在系统提示中以 json 的格式提供工具调用的格式和字段描述。内容以 `[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_141]\n`开头，`[UNUSED_TOKEN_145]` 结尾，`name=[UNUSED_TOKEN_141]` 体现了这是来自工具的指令。InternLM2-Chat 支持 system 角色对模型的提示和约束多次出现。所以我们会看到前面还有关于对话的要求。 -2. 模型在接受到用户指令后，会以流式的形式调用工具，及自然地生成文字进行思考/回应用户，然后输出`[UNUSED_TOKEN_144][UNUSED_TOKEN_141]`。`[UNUSED_TOKEN_144]`表示要调用外部插件，同时 `[UNUSED_TOKEN_141]` 表示调用的是常规工具。然后模型输出 json 格式的工具调用内容，再以 `[UNUSED_TOKEN_143]` 表示工具调用结束。 -3. 系统返回工具调用结果，以 `[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_141]`开头，表示是来自环境关于工具调用的反馈，内容是 json 格式，`{"temperature": 22}`，以`[UNUSED_TOKEN_145]`结尾。 +1. 首先，在系统提示中以 json 的格式提供工具调用的格式和字段描述。内容以 `<|im_start|>system name=<|plugin|>\n`开头，`<|im_end|>` 结尾，`name=<|plugin|>` 体现了这是来自工具的指令。InternLM2-Chat 支持 system 角色对模型的提示和约束多次出现。所以我们会看到前面还有关于对话的要求。 +2. 模型在接受到用户指令后，会以流式的形式调用工具，及自然地生成文字进行思考/回应用户，然后输出`<|action_start|><|plugin|>`。`<|action_start|>`表示要调用外部插件，同时 `<|plugin|>` 表示调用的是常规工具。然后模型输出 json 格式的工具调用内容，再以 `<|action_end|>` 表示工具调用结束。 +3. 系统返回工具调用结果，以 `<|im_start|>environment name=<|plugin|>`开头，表示是来自环境关于工具调用的反馈，内容是 json 格式，`{"temperature": 22}`，以`<|im_end|>`结尾。 ### 代码解释器 InternLM2-Chat 支持使用代码解释器解决复杂数学问题和进行数据分析。整个调用流程和通用工具调用类似，如下所示 ``` -[UNUSED_TOKEN_146]system -你是书生浦语2，一个无害的人工智能助手[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_142] +<|im_start|>system +你是书生浦语2，一个无害的人工智能助手<|im_end|> +<|im_start|>system name=<|interpreter|> 你现在可以使用一个支持 Python 代码执行的 Jupyter 笔记本环境。只需向 python 发送代码，即可在这个有状态环境中进行运行。这个功能适用于: - 数据分析或处理（如数据操作和图形制作） - 复杂计算（如数学和物理问题） @@ -88,15 +88,15 @@ InternLM2-Chat 支持使用代码解释器解决复杂数学问题和进行数 - 文本处理和分析（包括文本分析和自然语言处理） - 机器学习和数据科学（模型训练和数据可视化展示） - 文件操作和数据导入（处理CSV、JSON等格式文件） -[UNUSED_TOKEN_146]user +<|im_start|>user 请帮我对该数据集进行数据处理并可视化。 -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user name=file -[{"path": "data.csv", size='10K'}][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>user name=file +[{"path": "data.csv", size='10K'}]<|im_end|> +<|im_start|>assistant 我已经帮您处理了数据并进行了可视化。 -[UNUSED_TOKEN_144][UNUSED_TOKEN_142] +<|action_start|><|interpreter|> ```python import plotly.express as px import pandas as pd @@ -116,34 +116,34 @@ fig.update_traces(hovertemplate='Date: %{text}
Wind Direction 9am: %{x # Show the plot fig.show() -```[UNUSED_TOKEN_143] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_142] +```<|action_end|> +<|im_end|> +<|im_start|>environment name=<|interpreter|> ![image](xxx.png) -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -由于代码输出没有包含在这里，我无法提供具体的图表内容。但是，如果代码执行无误，它会显示一个极坐标图，其中包含两个填充区域，一个代表上午9点的风向与降雨量的关系，另一个代表下午3点的风向与降雨量的关系。每个方向上的值是根据提供的数据集计算得到的平均降雨量。图表应该有一个清晰的标题、图例，并且能够直观地比较不同风向下的降雨量。由于使用了暗色主题，图表的整体外观应该是深色背景上的亮色线条和填充区域。[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -你能解释一下代码吗[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>assistant +由于代码输出没有包含在这里，我无法提供具体的图表内容。但是，如果代码执行无误，它会显示一个极坐标图，其中包含两个填充区域，一个代表上午9点的风向与降雨量的关系，另一个代表下午3点的风向与降雨量的关系。每个方向上的值是根据提供的数据集计算得到的平均降雨量。图表应该有一个清晰的标题、图例，并且能够直观地比较不同风向下的降雨量。由于使用了暗色主题，图表的整体外观应该是深色背景上的亮色线条和填充区域。<|im_end|> +<|im_start|>user +你能解释一下代码吗<|im_end|> +<|im_start|>assistant 我使用的是Python的Plotly库来创建一个极坐标图，以展示风向与降雨量之间的关系。代码中首先创建了一个Plotly的Figure对象。接着，我添加了两个`Scatterpolar`追踪。第一个追踪展示的是上午9点的风向与降雨量的平均值的关系，第二个追踪展示的是下午3点的风向与降雨量的平均值的关系。在这两个追踪中，`r`参数代表降雨量的平均值，`theta`参数代表风向。`fill='toself'`表示图形以自身为边界进行填充。然后我更新了图表的布局，隐藏了径向轴，添加了图例，设置了标题和标题字体，选择了暗色主题，并设定了图表的背景色、宽度和高度。最后，使用`fig.show()`展示了图表。 -[UNUSED_TOKEN_145] +<|im_end|> ``` -1. 首先在系统提示中提供代码解释器的格式和字段描述。内容以 `[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_142]\n`开头，`[UNUSED_TOKEN_145]` 结尾，`name=[UNUSED_TOKEN_142]` 体现了这是来自代码解释器的指令。InternLM2-Chat 支持 system 角色对模型的提示和约束多次出现。所以我们会看到前面还有关于对话的要求。 -2. 用户可以上传一个文件，并对模型提出要求，文件的上传会以单独的形式向模型发出一条指令，以 `[UNUSED_TOKEN_146]user name=file` 开头，以 json 形式给出路径和文件大小` -[{"path": "data.csv", size='10K'}]`，以 `[UNUSED_TOKEN_145]`结尾。 -2. 模型在接受到用户指令后，会以流式的形式调用工具，及自然地生成文字进行思考/回应用户，然后输出`[UNUSED_TOKEN_144][UNUSED_TOKEN_142]`。`[UNUSED_TOKEN_144]`表示要调用外部插件，同时 `[UNUSED_TOKEN_142]` 表示调用的是代码解释器。然后模型输出 markdown 中 python 代码块格式代码内容，再以 `[UNUSED_TOKEN_143]` 表示工具调用结束。 -3. 系统会执行代码块中的代码，然后返回调用结果，以 `[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_142]`开头，表示是来自环境关于代码解释器执行的输出，以`[UNUSED_TOKEN_145]`结尾。 +1. 首先在系统提示中提供代码解释器的格式和字段描述。内容以 `<|im_start|>system name=<|interpreter|>\n`开头，`<|im_end|>` 结尾，`name=<|interpreter|>` 体现了这是来自代码解释器的指令。InternLM2-Chat 支持 system 角色对模型的提示和约束多次出现。所以我们会看到前面还有关于对话的要求。 +2. 用户可以上传一个文件，并对模型提出要求，文件的上传会以单独的形式向模型发出一条指令，以 `<|im_start|>user name=file` 开头，以 json 形式给出路径和文件大小` +[{"path": "data.csv", size='10K'}]`，以 `<|im_end|>`结尾。 +2. 模型在接受到用户指令后，会以流式的形式调用工具，及自然地生成文字进行思考/回应用户，然后输出`<|action_start|><|interpreter|>`。`<|action_start|>`表示要调用外部插件，同时 `<|interpreter|>` 表示调用的是代码解释器。然后模型输出 markdown 中 python 代码块格式代码内容，再以 `<|action_end|>` 表示工具调用结束。 +3. 系统会执行代码块中的代码，然后返回调用结果，以 `<|im_start|>environment name=<|interpreter|>`开头，表示是来自环境关于代码解释器执行的输出，以`<|im_end|>`结尾。 ### 同时使用工具和代码解释器 InternLM2-Chat 能够在一个对话过程中自主选择调用工具或代码解释器。在工具和代码解释器同时开启的情况下，只需要将各自的系统提示合并在一起给模型即可。一个调用工具和代码解释器的对话历史样例如下。 ``` -[UNUSED_TOKEN_146]system -你是书生浦语2，一个无害的人工智能助手[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_142] +<|im_start|>system +你是书生浦语2，一个无害的人工智能助手<|im_end|> +<|im_start|>system name=<|interpreter|> 你现在可以使用一个支持 Python 代码执行的 Jupyter 笔记本环境。只需向 python 发送代码，即可在这个有状态环境中进行运行。这个功能适用于: - 数据分析或处理（如数据操作和图形制作） - 复杂计算（如数学和物理问题） @@ -151,7 +151,7 @@ InternLM2-Chat 能够在一个对话过程中自主选择调用工具或代码 - 文本处理和分析（包括文本分析和自然语言处理） - 机器学习和数据科学（模型训练和数据可视化展示） - 文件操作和数据导入（处理CSV、JSON等格式文件） -[UNUSED_TOKEN_146]system name=[UNUSED_TOKEN_141] +<|im_start|>system name=<|plugin|> [ { "name": "get_current_weather", @@ -169,16 +169,16 @@ InternLM2-Chat 能够在一个对话过程中自主选择调用工具或代码 }, } ] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user +<|im_end|> +<|im_start|>user 请帮我对该数据集进行数据处理并可视化。 -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user name=file -[{"path": "data.csv", size='10K'}][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>user name=file +[{"path": "data.csv", size='10K'}]<|im_end|> +<|im_start|>assistant 我已经帮您处理了数据并进行了可视化。 -[UNUSED_TOKEN_144][UNUSED_TOKEN_142] +<|action_start|><|interpreter|> ```python import plotly.express as px import pandas as pd @@ -198,25 +198,25 @@ fig.update_traces(hovertemplate='Date: %{text}
Wind Direction 9am: %{x # Show the plot fig.show() -```[UNUSED_TOKEN_143] -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_142] +```<|action_end|> +<|im_end|> +<|im_start|>environment name=<|interpreter|> ![image](xxx.png) -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -由于代码输出没有包含在这里，我无法提供具体的图表内容。但是，如果代码执行无误，它会显示一个极坐标图，其中包含两个填充区域，一个代表上午9点的风向与降雨量的关系，另一个代表下午3点的风向与降雨量的关系。每个方向上的值是根据提供的数据集计算得到的平均降雨量。图表应该有一个清晰的标题、图例，并且能够直观地比较不同风向下的降雨量。由于使用了暗色主题，图表的整体外观应该是深色背景上的亮色线条和填充区域。[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -你能解释一下代码吗[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant +<|im_end|> +<|im_start|>assistant +由于代码输出没有包含在这里，我无法提供具体的图表内容。但是，如果代码执行无误，它会显示一个极坐标图，其中包含两个填充区域，一个代表上午9点的风向与降雨量的关系，另一个代表下午3点的风向与降雨量的关系。每个方向上的值是根据提供的数据集计算得到的平均降雨量。图表应该有一个清晰的标题、图例，并且能够直观地比较不同风向下的降雨量。由于使用了暗色主题，图表的整体外观应该是深色背景上的亮色线条和填充区域。<|im_end|> +<|im_start|>user +你能解释一下代码吗<|im_end|> +<|im_start|>assistant 我使用的是Python的Plotly库来创建一个极坐标图，以展示风向与降雨量之间的关系。代码中首先创建了一个Plotly的Figure对象。接着，我添加了两个`Scatterpolar`追踪。第一个追踪展示的是上午9点的风向与降雨量的平均值的关系，第二个追踪展示的是下午3点的风向与降雨量的平均值的关系。在这两个追踪中，`r`参数代表降雨量的平均值，`theta`参数代表风向。`fill='toself'`表示图形以自身为边界进行填充。然后我更新了图表的布局，隐藏了径向轴，添加了图例，设置了标题和标题字体，选择了暗色主题，并设定了图表的背景色、宽度和高度。最后，使用`fig.show()`展示了图表。 -[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]user -我想了解今天上海的天气[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -好的，我将为你查询上海的天气。[UNUSED_TOKEN_144][UNUSED_TOKEN_141] -{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}[UNUSED_TOKEN_143][UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]environment name=[UNUSED_TOKEN_141] -{"temperature": 22}[UNUSED_TOKEN_145] -[UNUSED_TOKEN_146]assistant -上海的天气是 22 摄氏度[UNUSED_TOKEN_145] +<|im_end|> +<|im_start|>user +我想了解今天上海的天气<|im_end|> +<|im_start|>assistant +好的，我将为你查询上海的天气。<|action_start|><|plugin|> +{"name": "get_current_weather", "parameters": {"location": "Shanghai"}}<|action_end|><|im_end|> +<|im_start|>environment name=<|plugin|> +{"temperature": 22}<|im_end|> +<|im_start|>assistant +上海的天气是 22 摄氏度<|im_end|> ``` diff --git a/chat/web_demo.py b/chat/web_demo.py index be65549..1368fc4 100644 --- a/chat/web_demo.py +++ b/chat/web_demo.py @@ -178,9 +178,9 @@ def prepare_generation_config(): return generation_config -user_prompt = "[UNUSED_TOKEN_146]user\n{user}[UNUSED_TOKEN_145]\n" -robot_prompt = "[UNUSED_TOKEN_146]assistant\n{robot}[UNUSED_TOKEN_145]\n" -cur_query_prompt = "[UNUSED_TOKEN_146]user\n{user}[UNUSED_TOKEN_145]\n[UNUSED_TOKEN_146]assistant\n" +user_prompt = "<|im_start|>user\n{user}<|im_end|>\n" +robot_prompt = "<|im_start|>assistant\n{robot}<|im_end|>\n" +cur_query_prompt = "<|im_start|>user\n{user}<|im_end|>\n<|im_start|>assistant\n" def combine_history(prompt): @@ -189,7 +189,7 @@ def combine_history(prompt): "You are InternLM (书生·浦语), a helpful, honest, and harmless AI assistant developed by Shanghai " "AI Laboratory (上海人工智能实验室)." ) - total_prompt = f"[UNUSED_TOKEN_146]system\n{meta_instruction}[UNUSED_TOKEN_145]\n" + total_prompt = f"<|im_start|>system\n{meta_instruction}<|im_end|>\n" for message in messages: cur_content = message["content"] if message["role"] == "user":