ai/devstral-small-2 repository overview

docker pull mistralllm/vllm_devstral:latest
docker run -it mistralllm/vllm_devstral:latest

python -c "import mistral_common; print(mistral_common.__version__)"

vllm serve mistralai/Devstral-Small-2-24B-Instruct-2512 --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

import requests
import json
from huggingface_hub import hf_hub_download


url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}

model = "mistralai/Devstral-Small-2-24B-Instruct-2512"

def load_system_prompt(repo_id: str, filename: str) -> str:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()
    return system_prompt

SYSTEM_PROMPT = load_system_prompt(model, "CHAT_SYSTEM_PROMPT.txt")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "<your-command>",
            },
        ],
    },
]

data = {"model": model, "messages": messages, "temperature": 0.15}

# Devstral Small 2 supports tool calling. If you want to use tools, follow this:
# tools = [ # Define tools for vLLM
#     {
#         "type": "function",
#         "function": {
#             "name": "git_clone",
#             "description": "Clone a git repository",
#             "parameters": {
#                 "type": "object",
#                 "properties": {
#                     "url": {
#                         "type": "string",
#                         "description": "The url of the git repository",
#                     },
#                 },
#                 "required": ["url"],
#             },
#         },
#     }
# ] 
# data = {"model": model, "messages": messages, "temperature": 0.15, "tools": tools} # Pass tools to payload.

response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])

uv pip install git+https://github.com/huggingface/transformers

import torch
from transformers import (
    Mistral3ForConditionalGeneration,
    MistralCommonBackend,
)

model_id = "mistralai/Devstral-Small-2-24B-Instruct-2512"

tokenizer = MistralCommonBackend.from_pretrained(model_id)
model = Mistral3ForConditionalGeneration.from_pretrained(model_id, device_map="auto")
model = model.to(torch.bfloat16)

SP = """You are operating as and within Mistral Vibe, a CLI coding-agent built by Mistral AI and powered by default by the Devstral family of models. It wraps Mistral's Devstral models to enable natural language interaction with a local codebase. Use the available tools when helpful.

You can:

- Receive user prompts, project context, and files.
- Send responses and emit function calls (e.g., shell commands, code edits).
- Apply patches, run commands, based on user approvals.

Answer the user's request using the relevant tool(s), if they are available. Check that all the required parameters for each tool call are provided or can reasonably be inferred from context. IF there are no relevant tools or there are missing values for required parameters, ask the user to supply these values; otherwise proceed with the tool calls. If the user provides a specific value for a parameter (for example provided in quotes), make sure to use that value EXACTLY. DO NOT make up values for or ask about optional parameters. Carefully analyze descriptive terms in the request as they may indicate required parameter values that should be included even if not explicitly quoted.

Always try your hardest to use the tools to answer the user's request. If you can't use the tools, explain why and ask the user for more information.

Act as an agentic assistant, if a user asks for a long task, break it down and do it step by step.

When you want to commit changes, you will always use the 'git commit' bash command. It will always
be suffixed with a line telling it was generated by Mistral Vibe with the appropriate co-authoring information.
The format you will always uses is the following heredoc.

```bash
git commit -m "<Commit message here>

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <[email protected]>"
```"""

input = {
    "messages": [
        {
            "role": "system",
            "content": SP,
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Can you implement in Python a method to compute the fibonnaci sequence at the `n`th element with `n` a parameter passed to the function ? You should start the sequence from 1, previous values are invalid.\nThen run the Python code for the function for n=5 and give the answer.",
                }
            ],
        },
    ],
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "add_number",
                "description": "Add two numbers.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "a": {"type": "string", "description": "The first number."},
                        "b": {"type": "string", "description": "The second number."},
                    },
                    "required": ["a", "b"],
                },
            },
        },
        {
            "type": "function",
            "function": {
                "name": "multiply_number",
                "description": "Multiply two numbers.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "a": {"type": "string", "description": "The first number."},
                        "b": {"type": "string", "description": "The second number."},
                    },
                    "required": ["a", "b"],
                },
            },
        },
        {
            "type": "function",
            "function": {
                "name": "substract_number",
                "description": "Substract two numbers.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "a": {"type": "string", "description": "The first number."},
                        "b": {"type": "string", "description": "The second number."},
                    },
                    "required": ["a", "b"],
                },
            },
        },
        {
            "type": "function",
            "function": {
                "name": "write_a_story",
                "description": "Write a story about science fiction and people with badass laser sabers.",
                "parameters": {},
            },
        },
        {
            "type": "function",
            "function": {
                "name": "terminal",
                "description": "Perform operations from the terminal.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "command": {
                            "type": "string",
                            "description": "The command you wish to launch, e.g `ls`, `rm`, ...",
                        },
                        "args": {
                            "type": "string",
                            "description": "The arguments to pass to the command.",
                        },
                    },
                    "required": ["command"],
                },
            },
        },
        {
            "type": "function",
            "function": {
                "name": "python",
                "description": "Call a Python interpreter with some Python code that will be ran.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "code": {
                            "type": "string",
                            "description": "The Python code to run",
                        },
                        "result_variable": {
                            "type": "string",
                            "description": "Variable containing the result you'd like to retrieve from the execution.",
                        },
                    },
                    "required": ["code", "result_variable"],
                },
            },
        },
    ],
}

tokenized = tokenizer.apply_chat_template(
    conversation=input["messages"],
    tools=input["tools"],
    return_tensors="pt",
    return_dict=True,
)

input_ids = tokenized["input_ids"].to(device="cuda")

output = model.generate(
    input_ids,
    max_new_tokens=200,
)[0]

decoded_output = tokenizer.decode(output[len(tokenized["input_ids"][0]) :])
print(decoded_output)