unsloth/Ministral-3-3B-Instruct-2512-bnb-4bit

pip install vllm --upgrade

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

vllm serve mistralai/Ministral-3-3B-Instruct-2512 \
  --enable-auto-tool-choice --tool-call-parser mistral

from datetime import datetime, timedelta

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.15
MAX_TOK = 262144

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


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()
    today = datetime.today().strftime("%Y-%m-%d")
    yesterday = (datetime.today() - timedelta(days=1)).strftime("%Y-%m-%d")
    model_name = repo_id.split("/")[-1]
    return system_prompt.format(name=model_name, today=today, yesterday=yesterday)


SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]

print(messages)


response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    max_tokens=MAX_TOK,
)

print(response.choices[0].message.content)

import json
from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.15
MAX_TOK = 262144

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


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, "SYSTEM_PROMPT.txt")

image_url = "https://math-coaching.com/img/fiche/46/expressions-mathematiques.jpg"


def my_calculator(expression: str) -> str:
    return str(eval(expression))


tools = [
    {
        "type": "function",
        "function": {
            "name": "my_calculator",
            "description": "A calculator that can evaluate a mathematical expression.",
            "parameters": {
                "type": "object",
                "properties": {
                    "expression": {
                        "type": "string",
                        "description": "The mathematical expression to evaluate.",
                    },
                },
                "required": ["expression"],
            },
        },
    },
    {
        "type": "function",
        "function": {
            "name": "rewrite",
            "description": "Rewrite a given text for improved clarity",
            "parameters": {
                "type": "object",
                "properties": {
                    "text": {
                        "type": "string",
                        "description": "The input text to rewrite",
                    }
                },
            },
        },
    },
]

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "Thanks to your calculator, compute the results for the equations that involve numbers displayed in the image.",
            },
            {
                "type": "image_url",
                "image_url": {
                    "url": image_url,
                },
            },
        ],
    },
]

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    max_tokens=MAX_TOK,
    tools=tools,
    tool_choice="auto",
)

tool_calls = response.choices[0].message.tool_calls

results = []
for tool_call in tool_calls:
    function_name = tool_call.function.name
    function_args = tool_call.function.arguments
    if function_name == "my_calculator":
        result = my_calculator(**json.loads(function_args))
        results.append(result)

messages.append({"role": "assistant", "tool_calls": tool_calls})
for tool_call, result in zip(tool_calls, results):
    messages.append(
        {
            "role": "tool",
            "tool_call_id": tool_call.id,
            "name": tool_call.function.name,
            "content": result,
        }
    )


response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    max_tokens=MAX_TOK,
)

print(response.choices[0].message.content)

from openai import OpenAI
from huggingface_hub import hf_hub_download

# Modify OpenAI's API key and API base to use vLLM's API server.
openai_api_key = "EMPTY"
openai_api_base = "http://localhost:8000/v1"

TEMP = 0.15
MAX_TOK = 262144

client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)

models = client.models.list()
model = models.data[0].id


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, "SYSTEM_PROMPT.txt")

messages = [
    {"role": "system", "content": SYSTEM_PROMPT},
    {
        "role": "user",
        "content": "Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.",
    },
]

response = client.chat.completions.create(
    model=model,
    messages=messages,
    temperature=TEMP,
    max_tokens=MAX_TOK,
)

assistant_message = response.choices[0].message.content
print(assistant_message)

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

pip install mistral-common --upgrade

import torch
from transformers import Mistral3ForConditionalGeneration, MistralCommonBackend

model_id = "mistralai/Ministral-3-3B-Instruct-2512"

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

image_url = "https://static.wikia.nocookie.net/essentialsdocs/images/7/70/Battle.png/revision/latest?cb=20220523172438"

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What action do you think I should take in this situation? List all the possible actions and explain why you think they are good or bad.",
            },
            {"type": "image_url", "image_url": {"url": image_url}},
        ],
    },
]

tokenized = tokenizer.apply_chat_template(messages, return_tensors="pt", return_dict=True)

tokenized["input_ids"] = tokenized["input_ids"].to(device="cuda")
tokenized["pixel_values"] = tokenized["pixel_values"].to(dtype=torch.bfloat16, device="cuda")
image_sizes = [tokenized["pixel_values"].shape[-2:]]

output = model.generate(
    **tokenized,
    image_sizes=image_sizes,
    max_new_tokens=512,
)[0]

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

from transformers import Mistral3ForConditionalGeneration, FineGrainedFP8Config

model_id = "mistralai/Ministral-3-3B-Instruct-2512"
model = Mistral3ForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    quantization_config=FineGrainedFP8Config(dequantize=True)
)