chat-prompts

Crates.io	chat-prompts
lib.rs	chat-prompts
version	0.35.0
created_at	2023-10-23 07:02:27.870815+00
updated_at	2025-09-15 02:05:08.094777+00
description	Chat prompt template
homepage
repository	https://github.com/LlamaEdge/LlamaEdge
max_upload_size
id	1011016
size	470,880

Xin Liu (apepkuss)

documentation

https://docs.rs/chat-prompts/

README

Prompt Templates for LLMs

chat-prompts is part of LlamaEdge API Server project. It provides a collection of prompt templates that are used to generate prompts for the LLMs (See models in huggingface.co/second-state).

Prompt Templates

The available prompt templates are listed below:

baichuan-2

Prompt string

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:

Example: second-state/Baichuan2-13B-Chat-GGUF

codellama-instruct

Prompt string

<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]

Example: second-state/CodeLlama-13B-Instruct-GGUF

codellama-super-instruct

Prompt string

<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

Example: second-state/CodeLlama-70b-Instruct-hf-GGUF

chatml

Prompt string

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

Example: second-state/Yi-34B-Chat-GGUF

chatml-think

Prompt string

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

Example: Tessa-T1

chatml-tool

Prompt string

<|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

Example

<|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

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

deepseek-chat

Prompt string

User: {user_message_1}

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

Assistant:

Example: second-state/Deepseek-LLM-7B-Chat-GGUF

deepseek-chat-2

Prompt string

<|begin_of_sentence|>{system_message}

User: {user_message_1}

Assistant: {assistant_message_1}<|end_of_sentence|>User: {user_message_2}

Assistant:

Example: second-state/DeepSeek-Coder-V2-Lite-Instruct-GGUF

deepseek-chat-25

Prompt string

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

Example: second-state/DeepSeek-V2.5-GGUF

deepseek-coder

Prompt string

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

Example: second-state/Deepseek-Coder-6.7B-Instruct-GGUF

embedding
- Prompt string This prompt template is only used for embedding models. It works as a placeholder, therefore, it has no concrete prompt string.
- Example: second-state/E5-Mistral-7B-Instruct-Embedding-GGUF

exaone-chat

Prompt string

[|system|]{system_message}[|endofturn|]
[|user|]{user_message_1}
[|assistant|]{assistant_message_1}[|endofturn|]
[|user|]{user_message_2}
[|assistant|]

Example: second-state/EXAONE-3.5-32B-Instruct-GGUF

exaone-deep-chat

Prompt string

[|system|]{system_message}[|endofturn|]
[|user|]{user_message_1}
[|assistant|]{assistant_message_1}[|endofturn|]
[|user|]{user_message_2}
[|assistant|]<thought>

Example: second-state/EXAONE-Deep-32B-GGUF

falcon3

Prompt string

<|system|>
{system_message}
<|user|>
{user_message}
<|assistant|>

Example: second-state/Falcon3-7B-Instruct-GGUF

functionary-31

Prompt string

<|start_header_id|>system<|end_header_id|>

Environment: ipython

Cutting Knowledge Date: December 2023


You have access to the following functions:

Use the function 'get_current_weather' to 'Get the current weather'
{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}},"required":["location"]}}


Think very carefully before calling functions.
If a you choose to call a function ONLY reply in the following format:
<{start_tag}={function_name}>{parameters}{end_tag}
where

start_tag => `<function`
parameters => a JSON dict with the function argument name as key and function argument value as value.
end_tag => `</function>`

Here is an example,
<function=example_function_name>{"example_name": "example_value"}</function>

Reminder:
- If looking for real time information use relevant functions before falling back to brave_search
- Function calls MUST follow the specified format, start with <function= and end with </function>
- Required parameters MUST be specified
- Only call one function at a time
- Put the entire function call reply on one line

<|eot_id|><|start_header_id|>user<|end_header_id|>

What is the weather like in Beijing today?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Example: second-state/functionary-small-v3.1-GGUF

functionary-32

Prompt string

<|start_header_id|>system<|end_header_id|>

You are capable of executing available function(s) if required.
Only execute function(s) when absolutely necessary.
Ask for the required input to:recipient==all
Use JSON for function arguments.
Respond in this format:
>>>${recipient}
${content}
Available functions:
// Supported function definitions that should be called when necessary.
namespace functions {

    // Get the current weather
    type get_current_weather = (_: {

        // The city and state, e.g. San Francisco, CA
        location: string,

    }) => any;


} // namespace functions<|eot_id|><|start_header_id|>user<|end_header_id|>

What is the weather like in Beijing today?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Example: second-state/functionary-small-v3.2-GGUF

gemma-3

Prompt string

<bos><start_of_turn>user
{user_message_1}<end_of_turn>
<start_of_turn>model
{model_message_1}<end_of_turn>model
<start_of_turn>user
{system_prompt}
{user_message_2}<end_of_turn>
<start_of_turn>model

Example: second-state/gemma-3-27b-it-GGUF

gemma-instruct

Prompt string

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

Example: second-state/gemma-2-27b-it-GGUF

glm-4-chat

Prompt string

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

Example: second-state/glm-4-9b-chat-GGUF

gpt-oss

Prompt string

<|start|>system<|message|>
You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-06
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.
<|end|>

<|start|>user<|message|>Hello!<|end|>
<|start|>assistant<|channel|>final<|message|>Hi there!<|end|>
<|start|>user<|message|>What's your favorite color?<|end|>
<|start|>assistant

Example: second-state/gpt-oss-20b-GGUF

human-assistant
- Prompt string
```
Human: {input_1}\n\nAssistant:{output_1}Human: {input_2}\n\nAssistant:
```
- Example: second-state/OrionStar-Yi-34B-Chat-Llama-GGUF
intel-neural
- Prompt string
```
### System:
{system}
### User:
{usr}
### Assistant:
```
- Example: second-state/Neural-Chat-7B-v3-3-GGUF

llama-2-chat

Prompt string

<s>[INST] <<SYS>>
{system_message}
<</SYS>>

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

llama-3-chat

Prompt string

<|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|>

llama-3-tool

Prompt string

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_message}<|eot_id|><|start_header_id|>user<|end_header_id|>

Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.

Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.

[{"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","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]}},"required":["location","unit"]}}}]

Question: {user_message}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

llama-4-chat

Prompt string

Chat

<|begin_of_text|><|header_start|>system<|header_end|>

{system_message}<|eot|>
<|header_start|>user<|header_end|>

{user_message_1}<|eot|>
<|header_start|>assistant<|header_end|>

{assistant_message_1}<|eot|>
<|header_start|>user<|header_end|>

{user_message_2}<|eot|><|header_start|>assistant<|header_end|>

Tool use

Prompt with user question and tool info

Expand to see the example

<|begin_of_text|><|header_start|>system<|header_end|>

You are a helpful assistant.<|eot|>
<|header_start|>user<|header_end|>

Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.

Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.
Do not use variables.

[
  {
    "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",
            "description": "The temperature unit to use. Infer this from the users location.",
            "enum": [
              "celsius",
              "fahrenheit"
            ]
          }
        },
        "required": [
          "location",
          "unit"
        ]
      }
    }
  },
  {
    "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",
            "description": "The temperature unit to use. Infer this from the users location.",
            "enum": [
              "celsius",
              "fahrenheit"
            ]
          }
        },
        "required": [
          "location",
          "unit"
        ]
      }
    }
  },
  {
    "type": "function",
    "function": {
      "name": "sum",
      "description": "Calculate the sum of two numbers",
      "parameters": {
        "type": "object",
        "properties": {
          "a": {
            "type": "integer",
            "description": "the left hand side number"
          },
          "b": {
            "type": "integer",
            "description": "the right hand side number"
          }
        },
        "required": [
          "a",
          "b"
        ]
      }
    }
  }
]

Question: How is the weather of Beijing, China in celsius?<|eot|><|header_start|>assistant<|header_end|>

Prompt with tool results

<|begin_of_text|><|header_start|>system<|header_end|>

You are a helpful assistant.<|eot|>
<|header_start|>user<|header_end|>

How is the weather of Beijing, China in celsius?<|eot|>
<|header_start|>assistant<|header_end|>

{"name":"get_current_weather","arguments":"{\"location\":\"Beijing, China\",\"unit\":\"celsius\"}"}<|eot|>
<|header_start|>ipython<|header_end|>

{"temperature":"30","unit":"celsius"}<|eot|><|header_start|>assistant<|header_end|>

Example: second-state/Llama-4-Scout-17B-16E-Instruct-GGUF

mediatek-breeze

Prompt string

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

Example: second-state/Breeze-7B-Instruct-v1_0-GGUF

megrez

Prompt string

<|role_start|>system<|role_end|>{system_message}<|turn_end|><|role_start|>user<|role_end|>{user_message}<|turn_end|><|role_start|>assistant<|role_end|>

Example: second-state/Megrez-3B-Instruct-GGUF

mistral-instruct

Prompt string

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

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

mistrallite

Prompt string

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

Example: second-state/MistralLite-7B-GGUF

mistral-small-chat

Prompt string

<s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST]

Example: second-state/Mistral-Small-24B-Instruct-2501-GGUF

mistral-small-tool

Prompt string

<s>[INST] {user_message_1}[/INST][TOOL_CALLS] [{tool_call_1},{tool_call_2}]</s>[TOOL_RESULTS] {tool_result_1}[/TOOL_RESULTS] {assistant_message_1}</s>[AVAILABLE_TOOLS] [{tool_1},{tool_2}][/AVAILABLE_TOOLS][INST] {system_message}<0x0A><0x0A>{user_message_2}[/INST]

Example

[INST] What is the weather like in San Francisco in Celsius?[/INST][TOOL_CALLS] [{"id":"call_abc123","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"celsius\"}"}}]</s>[TOOL_RESULTS] {"id":"call_abc123","content":{"temperature":"30","unit":"celsius"}}[/TOOL_RESULTS] The current temperature in San Francisco is 30°C.</s>[INST] What is the weather like in San Francisco in the coming 24 hours in Celsius?[/INST][TOOL_CALLS] [{"id":"call_abc123","type":"function","function":{"name":"predict_weather","arguments":"{}"}}]</s>[TOOL_RESULTS] {"id":"call_abc124","content":{"temperature":"25","unit":"celsius"}}[/TOOL_RESULTS]

Example: second-state/Mistral-Small-24B-Instruct-2501-GGUF

mistral-tool

Prompt string

[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]

Example

[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]

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

moxin-chat

<s> [INST] {system_message}

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

Example: second-state/moxin-chat-7b-GGUF

moxin-instruct

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

Example: second-state/moxin-reasoning-7b-GGUF

nemotron-chat

<extra_id_0>System
{system_message}
<extra_id_1>User
{user_message_1}<extra_id_1>Assistant
{assistant_message_1}
<extra_id_1>User
{user_message_2}<extra_id_1>Assistant
{assistant_message_2}
<extra_id_1>User
{user_message_3}
<extra_id_1>Assistant\n

Example: second-state/Nemotron-Mini-4B-Instruct-GGUF

nemotron-tool

<extra_id_0>System
{system_message}
<tool> {tool_1} </tool>
<tool> {tool_2} </tool>


<extra_id_1>User
{user_message_1}<extra_id_1>Assistant
<toolcall> {tool_call_message} </toolcall>
<extra_id_1>Tool
{tool_result_message}
<extra_id_1>Assistant\n

Example: second-state/Nemotron-Mini-4B-Instruct-GGUF

octopus
- Prompt string
```
{system_prompt}\n\nQuery: {input_text} \n\nResponse:
```
- Example: second-state/Octopus-v2-GGUF
openchat
- Prompt string
```
GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant:
```
- Example: second-state/OpenChat-3.5-0106-GGUF
phi-2-instruct
- Prompt string
```
Instruct: <prompt>\nOutput:
```
- Example: second-state/phi-2-GGUF

phi-3-chat

Prompt string

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

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

phi-4-chat

Prompt string

<|im_start|>system<|im_sep|>
{system_message}<|im_end|>
<|im_start|>user<|im_sep|>
{user_message}<|im_end|>
<|im_start|>assistant<|im_sep|>

Example: second-state/phi-4-GGUF

qwen3-no-think

Prompt string

<|im_start|>system
You are a helpful assistant. Answer questions as concisely as possible.<|im_end|>
<|im_start|>user
{user_message_1}<|im_end|>
<|im_start|>assistant
{assistant_message_1}<|im_end|>
<|im_start|>user
{user_message_2}<|im_end|>
<|im_start|>assistant
<think>

</think>

Example: second-state/Qwen3-4B-GGUF

seed-instruct

Prompt string

<[begin▁of▁sentence]>system
{system_message}

<[end▁of▁sentence]><[begin▁of▁sentence]>user
{user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
{assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user
{user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant

Example: second-state/Seed-Coder-8B-Instruct-GGUF

seed-oss-think and seed-oss-no-think

Prompt string (seed-oss-think)

<seed:bos>system
You are Doubao, a helpful AI assistant.
<seed:eos>

<seed:bos>user
{user_message_1}
<seed:eos>

<seed:bos>assistant
<seed:think>{thinking_content}</seed:think>
{assistant_message_1}
<seed:eos>

<seed:bos>user
{user_message_2}
<seed:eos>

<seed:bos>assistant

Prompt string (seed-oss-no-think)

<seed:bos>system
You are Doubao, a helpful AI assistant.
<seed:eos>

<seed:bos>system
You are an intelligent assistant that can answer questions in one step without the need for reasoning and thinking, that is, your     thinking budget is 0. Next, please skip       the thinking process and directly start answering the user's questions.
<seed:eos>

<seed:bos>user
{user_message_1}
<seed:eos>

<seed:bos>assistant
{assistant_message_1}
<seed:eos>

<seed:bos>user
{user_message_2}
<seed:eos>

<seed:bos>assistant

Example: second-state/Seed-OSS-36B-Instruct-GGUF

seed-reasoning

Prompt string

<[begin▁of▁sentence]>user
{user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
{assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user
{user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant

Example: second-state/Seed-Coder-8B-Reasoning-GGUF

smol-vision

Prompt string

<|im_start|>
User: {user_message_1}<image>
Assistant: {assistant_message_1}
User: {user_message_2}
Assistant:

Example: second-state/SmolVLM2-2.2B-Instruct-GGUF

stablelm-zephyr
- Prompt string
```
<|user|>
{prompt}<|endoftext|>
<|assistant|>
```
- Example: second-state/stablelm-2-zephyr-1.6b-GGUF
vicuna-1.0-chat
- Prompt string
```
{system} USER: {prompt} ASSISTANT:
```
- Example: second-state/Wizard-Vicuna-13B-Uncensored-GGUF
vicuna-1.1-chat
- Prompt string
```
USER: {prompt}
ASSISTANT:
```
- Example: second-state/ChatAllInOne-Yi-34B-200K-V1-GGUF

vicuna-llava

Prompt string

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

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

wizard-coder
- Prompt string
```
{system}

### Instruction:
{instruction}

### Response:
```
- Example: second-state/WizardCoder-Python-7B-v1.0-GGUF

zephyr

Prompt string

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

Example: second-state/Zephyr-7B-Beta-GGUF

Commit count: 529

chat-prompts

documentation

README

Prompt Templates for LLMs

Prompt Templates

cargo fmt