Mistral’s ‘Small’ 24B Parameter Model Blows Minds—No Data Sent to China, Just Pure AI Power!

git clone https://github.com/alexander-uspenskiy/mistral.git
cd mistral

python -m venv venv
source venv/bin/activate  # On Windows use `venv\Scripts\activate`

pip install torch transformers

export HUGGINGFACE_HUB_TOKEN=your_token_here

python mistral.py

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import os
import time
import threading

# Check if MPS (Apple Silicon GPU) is available
device = torch.device("mps" if torch.backends.mps.is_available() else "cpu")

# Load the Mistral-Small-24B-Base-2501 model
model_name = "mistralai/Mistral-Small-24B-Instruct-2501"
token = os.getenv("HUGGINGFACE_HUB_TOKEN")

tokenizer = AutoTokenizer.from_pretrained(model_name, token=token)


model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map={"": device},
    torch_dtype=torch.float16,  # Optimized for M1 GPU
    token=token
)

def show_progress():
    while not stop_event.is_set():
        for char in "|/-\\":
            print(f"\rGenerating response {char}", end="", flush=True)
            time.sleep(0.1)

# Interactive terminal loop
print("mistralai/Mistral-Small-24B-Instruct-2501 Chat Interface (type 'exit' to quit)")
interaction_count = 0  # Initialize counter
while True:
    user_input = input("You: ")
    if user_input.lower() in ["exit", "quit"]:
        break

    inputs = tokenizer(user_input, return_tensors="pt").to(device)

    stop_event = threading.Event()
    progress_thread = threading.Thread(target=show_progress)
    progress_thread.start()

    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_length=200,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
            pad_token_id=tokenizer.eos_token_id  # Added to avoid warning
        )

    stop_event.set()
    progress_thread.join()
    print("\r", end="")  # Clear the progress line

    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    print(f"Mistral: {response}\n")

You: The bat and the ball costs $1.10 in total, bat is expensive than a ball costs $1.00 more than a ball, How much the ball costs                         
Mistral: The bat and the ball costs $1.10 in total, bat is expensive than a ball costs $1.00 more than a ball, How much the ball costs?
Let's denote the cost of the ball as \( B \) and the cost of the bat as \( B + 1.00 \).

According to the problem, the total cost of the bat and the ball is $1.10. Therefore, we can write the equation:

\[ B + (B + 1.00) = 1.10 \]

Simplifying the equation:

\[ 2B + 1.00 = 1.10 \]

Subtract 1.00 from both sides:

\[ 2B = 0.10 \]

Divide both sides by 2:

\[ B = 0.05 \]

So, the ball costs $0.05.