Magistral-Small-2507-GGUF

pip install -U vllm \
    --pre \
    --extra-index-url https://wheels.vllm.ai/nightly

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

vllm serve mistralai/Magistral-Small-2507 --reasoning-parser mistral --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2

from typing import Any
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 = 0.7
TOP_P = 0.95
MAX_TOK = 40_960

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) -> dict[str, Any]:
    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
    with open(file_path, "r") as file:
        system_prompt = file.read()

    index_begin_think = system_prompt.find("[THINK]")
    index_end_think = system_prompt.find("[/THINK]")

    return {
        "role": "system",
        "content": [
            {"type": "text", "text": system_prompt[:index_begin_think]},
            {
                "type": "thinking",
                "thinking": system_prompt[
                    index_begin_think + len("[THINK]") : index_end_think
                ],
                "closed": True,
            },
            {
                "type": "text",
                "text": system_prompt[index_end_think + len("[/THINK]") :],
            },
        ],
    }

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

query = "Write 4 sentences, each with at least 8 words. Now make absolutely sure that every sentence has exactly one word less than the previous sentence."
# or try out other queries
# query = "Exactly how many days ago did the French Revolution start? Today is June 4th, 2025."
# query = "Think about 5 random numbers. Verify if you can combine them with addition, multiplication, subtraction or division to 133"
# query = "If it takes 30 minutes to dry 12 T-shirts in the sun, how long does it take to dry 33 T-shirts?"

messages = [
    SYSTEM_PROMPT,
    {"role": "user", "content": query}
]
stream = client.chat.completions.create(
  model=model,
  messages=messages,
  stream=True,
  temperature=TEMP,
  top_p=TOP_P,
  max_tokens=MAX_TOK,
)

print("client: Start streaming chat completions...:\n")
printed_reasoning_content = False
answer = []

for chunk in stream:
    reasoning_content = None
    content = None
    # Check the content is reasoning_content or content
    if hasattr(chunk.choices[0].delta, "reasoning_content"):
        reasoning_content = chunk.choices[0].delta.reasoning_content
    elif hasattr(chunk.choices[0].delta, "content"):
        content = chunk.choices[0].delta.content

    if reasoning_content is not None:
        if not printed_reasoning_content:
            printed_reasoning_content = True
            print("Start reasoning:\n", end="", flush=True)
        print(reasoning_content, end="", flush=True)
    elif content is not None:
        # Extract and print the content
        if not reasoning_content and printed_reasoning_content:
            answer.extend(content)
        print(content, end="", flush=True)

if answer:
    print("\n\n=============\nAnswer\n=============\n")
    print("".join(answer))
else:
    print("\n\n=============\nNo Answer\n=============\n")
    print("No answer was generated by the model, probably because the maximum number of tokens was reached.")

# client: Start streaming chat completions...:
#
# Start reasoning:
# First, I need to write ...
# ...
#
#
# =============
# Answer
# =============
# 
# Here are four sentences where each has at least 8 words, and each subsequent sentence has exactly one word less than the previous one:

# 1. The quick brown fox jumps over the lazy dog and rests.
# 2. The lazy dog rests under the big shady tree peacefully.
# 3. The big shady tree provides ample shade during summer.
# 4. The tree's leaves are very lush and green.

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

pip install --upgrade mistral-common

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

from typing import Any
import torch

from huggingface_hub import hf_hub_download
from transformers import AutoModelForCausalLM, AutoTokenizer


TEMP = 0.7
TOP_P = 0.95
MAX_TOK = 40_960

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

    index_begin_think = system_prompt.find("[THINK]")
    index_end_think = system_prompt.find("[/THINK]")

    return {
        "role": "system",
        "content": [
            {"type": "text", "text": system_prompt[:index_begin_think]},
            {
                "type": "thinking",
                "thinking": system_prompt[
                    index_begin_think + len("[THINK]") : index_end_think
                ],
                "closed": True,
            },
            {
                "type": "text",
                "text": system_prompt[index_end_think + len("[/THINK]") :],
            },
        ],
    }


model_id = "mistralai/Magistral-Small-2507"
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
query = "Think about 5 random numbers. Verify if you can combine them with addition, multiplication, subtraction or division to 133."
# or try out other queries
# query = "Exactly how many days ago did the French Revolution start? Today is June 4th, 2025."
# query = "Write 4 sentences, each with at least 8 words. Now make absolutely sure that every sentence has exactly one word less than the previous sentence."
# query = "If it takes 30 minutes to dry 12 T-shirts in the sun, how long does it take to dry 33 T-shirts?"



tokenizer = AutoTokenizer.from_pretrained(model_id, tokenizer_type="mistral", use_fast=False)
model = AutoModelForCausalLM.from_pretrained(
    model_id, torch_dtype=torch.bfloat16, device_map="auto"
)

input_ids = tokenizer.apply_chat_template(
    [
        SYSTEM_PROMPT,
        {"role": "user", "content": query},
    ],
)

output = model.generate(
    input_ids=torch.tensor([input_ids], device=model.device),
    pad_token_id=tokenizer.pad_token_id,
    eos_token_id=tokenizer.eos_token_id,
    temperature=TEMP,
    top_p=TOP_P,
    do_sample=True,
    max_new_tokens=MAX_TOK,
)[0]

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

# [THINK]Alright, I need to think of 5 random numbers first. Let's say I pick the numbers 5, 10, 2, 7, and 3.
# 
# Now, I need to see if I can combine these numbers using addition, multiplication, subtraction, or division to get 133.
# ...
# ...
# ...
# But if we're to find any five numbers that can be combined to make 133, then yes, such sets exist, like the one demonstrated above.[/THINK]Yes, it is possible to combine some sets of five random numbers to make 133 using basic arithmetic operations. For example, the numbers 13, 10, 1, 2, and 3 can be combined as follows to make 133:
# 
# \[ (13 \times 10) + (3 \times (2 - 1)) = 130 + 3 = 133 \]
# 
# However, not all sets of five random numbers can be combined in this way to make 133. For instance, with the numbers 5, 10, 2, 7, and 3, it is not possible to combine them using the allowed operations to get exactly 133.
# 
# Therefore, the ability to combine five random numbers to make 133 depends on the specific numbers chosen.
# 
# $133 = (13 \times 10) + (3 \times (2 - 1))$</s>