LLM的提示模板

chat-prompts 是 LlamaEdge API 服务器 项目的一部分。它提供了一组提示模板，用于为LLM生成提示（见 huggingface.co/second-state 中的模型）。

提示模板

以下列出了可用的提示模板

• baichuan-2

  • 提示字符串

    以下内容为人类用户与与一位智能助手的对话。
    
    用户:你好！
    助手:
    

  • 示例： second-state/Baichuan2-13B-Chat-GGUF

• codellama-instruct

  • 提示字符串

    <s>[INST] <<SYS>>
    Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using ```: <</SYS>>
    
    {prompt} [/INST]
    

  • 示例： second-state/CodeLlama-13B-Instruct-GGUF

• codellama-super-instruct

  • 提示字符串

    <s>Source: system\n\n {system_prompt} <step> Source: user\n\n {user_message_1} <step> Source: assistant\n\n {ai_message_1} <step> Source: user\n\n {user_message_2} <step> Source: assistant\nDestination: user\n\n
    

  • 示例： second-state/CodeLlama-70b-Instruct-hf-GGUF

• chatml

  • 提示字符串

    <|im_start|>system
    {system_message}<|im_end|>
    <|im_start|>user
    {prompt}<|im_end|>
    <|im_start|>assistant
    

  • 示例： second-state/Yi-34B-Chat-GGUF

• chatml-tool

  • 提示字符串

    <|im_start|>system\n{system_message} Here are the available tools: <tools> [{tool_1}, {tool_2}] </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n<tool_call>\n{"arguments": <args-dict>, "name": <function-name>}\n</tool_call><|im_end|>
    <|im_start|>user
    {user_message}<|im_end|>
    <|im_start|>assistant
    

    • 示例

      <|im_start|>system\nYou are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"format":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","format"]}}},{"type":"function","function":{"name":"predict_weather","description":"Predict the weather in 24 hours","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"format":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","format"]}}}] </tools> Use the following pydantic model json schema for each tool call you will make: {"properties": {"arguments": {"title": "Arguments", "type": "object"}, "name": {"title": "Name", "type": "string"}}, "required": ["arguments", "name"], "title": "FunctionCall", "type": "object"} For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n<tool_call>\n{"arguments": <args-dict>, "name": <function-name>}\n</tool_call><|im_end|>
      <|im_start|>user
      Hey! What is the weather like in Beijing?<|im_end|>
      <|im_start|>assistant
      

  • 示例： second-state/Hermes-2-Pro-Llama-3-8B-GGUF

• deepseek-chat

  • 提示字符串

    User: {user_message_1}
    
    Assistant: {assistant_message_1}<｜end▁of▁sentence｜>User: {user_message_2}
    
    Assistant:
    

  • 示例： second-state/Deepseek-LLM-7B-Chat-GGUF

• deepseek-chat-2

  • 提示字符串

    <|begin_of_sentence|>{system_message}
    
    User: {user_message_1}
    
    Assistant: {assistant_message_1}<|end_of_sentence|>User: {user_message_2}
    
    Assistant:
    

  • 示例： second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF

• deepseek-coder

  • 提示字符串

    {system}
    ### Instruction:
    {question_1}
    ### Response:
    {answer_1}
    <|EOT|>
    ### Instruction:
    {question_2}
    ### Response:
    

  • 示例： second-state/Deepseek-Coder-6.7B-Instruct-GGUF

• embedding

  • 提示字符串 此提示模板仅用于嵌入模型。它作为一个占位符，因此没有具体的提示字符串。

  • 示例： second-state/E5-Mistral-7B-Instruct-Embedding-GGUF

• gemma-instruct

  • 提示字符串

    <bos><start_of_turn>user
    {user_message}<end_of_turn>
    <start_of_turn>model
    {model_message}<end_of_turn>model
    

  • 示例： second-state/gemma-2-27b-it-GGUF

• glm-4-chat

  • 提示字符串

    [gMASK]<|system|>
    {system_message}<|user|>
    {user_message_1}<|assistant|>
    {assistant_message_1}
    

  • 示例： second-state/glm-4-9b-chat-GGUF

• human-assistant

  • 提示字符串

    Human: {input_1}\n\nAssistant:{output_1}Human: {input_2}\n\nAssistant:
    

  • 示例： second-state/OrionStar-Yi-34B-Chat-Llama-GGUF

• intel-neural

  • 提示字符串

    ### System:
    {system}
    ### User:
    {usr}
    ### Assistant:
    

  • 示例： second-state/Neural-Chat-7B-v3-3-GGUF

• llama-2-chat

  • 提示字符串

    <s>[INST] <<SYS>>
    {system_message}
    <</SYS>>
    
    {user_message_1} [/INST] {assistant_message} </s><s>[INST] {user_message_2} [/INST]
    

• llama-3-chat

  • 提示字符串

    <|begin_of_text|><|start_header_id|>system<|end_header_id|>
    
    {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
    
    {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    
    {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
    
    {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
    

• mistral-instruct

  • 提示字符串

    <s>[INST] {user_message_1} [/INST]{assistant_message_1}</s>[INST] {user_message_2} [/INST]{assistant_message_2}</s>
    

  • 示例： second-state/Mistral-7B-Instruct-v0.3-GGUF

• mistrallite

  • 提示字符串

    <|prompter|>{user_message}</s><|assistant|>{assistant_message}</s>
    

  • 示例： second-state/MistralLite-7B-GGUF

• mistral-tool

  • 提示字符串

    [INST] {user_message_1} [/INST][TOOL_CALLS] [{tool_call_1}]</s>[TOOL_RESULTS]{tool_result_1}[/TOOL_RESULTS]{assistant_message_1}</s>[AVAILABLE_TOOLS] [{tool_1},{tool_2}][/AVAILABLE_TOOLS][INST] {user_message_2} [/INST]
    

    • 示例

      [INST] Hey! What is the weather like in Beijing and Tokyo? [/INST][TOOL_CALLS] [{"name":"get_current_weather","arguments":{"location": "Beijing, CN", "format": "celsius"}}]</s>[TOOL_RESULTS]Fine, with a chance of showers.[/TOOL_RESULTS]Today in Auckland, the weather is expected to be partly cloudy with a high chance of showers. Be prepared for possible rain and carry an umbrella if you're venturing outside. Have a great day!</s>[AVAILABLE_TOOLS] [{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}},{"type":"function","function":{"name":"predict_weather","description":"Predict the weather in 24 hours","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}][/AVAILABLE_TOOLS][INST] What is the weather like in Beijing now?[/INST]
      

  • 示例： second-state/Mistral-7B-Instruct-v0.3-GGUF

• octopus

  • 提示字符串

    {system_prompt}\n\nQuery: {input_text} \n\nResponse:
    

  • 示例： second-state/Octopus-v2-GGUF

• openchat

  • 提示字符串

    GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
    

  • 示例： second-state/OpenChat-3.5-0106-GGUF

• phi-2-instruct

  • 提示字符串

    Instruct: <prompt>\nOutput:
    

  • 示例： second-state/phi-2-GGUF

• phi-3-chat

  • 提示字符串

    <|system|>
    {system_message}<|end|>
    <|user|>
    {user_message_1}<|end|>
    <|assistant|>
    {assistant_message_1}<|end|>
    <|user|>
    {user_message_2}<|end|>
    <|assistant|>
    

  • 示例： second-state/Phi-3-medium-4k-instruct-GGUF

• solar-instruct

  • 提示字符串

    <s> ### User:
    {user_message}
    
    \### Assistant:
    {assistant_message}</s>
    

  • 示例： second-state/SOLAR-10.7B-Instruct-v1.0-GGUF

• stablelm-zephyr

  • 提示字符串

    <|user|>
    {prompt}<|endoftext|>
    <|assistant|>
    

  • 示例： second-state/stablelm-2-zephyr-1.6b-GGUF

• vicuna-1.0-chat

  • 提示字符串

    {system} USER: {prompt} ASSISTANT:
    

  • 示例： second-state/Wizard-Vicuna-13B-Uncensored-GGUF

• vicuna-1.1-chat

  • 提示字符串

    USER: {prompt}
    ASSISTANT:
    

  • 示例： second-state/ChatAllInOne-Yi-34B-200K-V1-GGUF

• vicuna-llava

  • 提示字符串

    <system_prompt>\nUSER:<image_embeddings>\n<textual_prompt>\nASSISTANT:
    

  • 示例： second-state/Llava-v1.6-Vicuna-7B-GGUF

• wizard-coder

  • 提示字符串

    {system}
    
    ### Instruction:
    {instruction}
    
    ### Response:
    

  • 示例： second-state/WizardCoder-Python-7B-v1.0-GGUF

• zephyr

  • 提示字符串

    <|system|>
    {system_prompt}</s>
    <|user|>
    {prompt}</s>
    <|assistant|>
    

  • 示例： second-state/Zephyr-7B-Beta-GGUF