Instructions to use MiniMaxAI/MiniMax-M2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MiniMaxAI/MiniMax-M2.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M2.1", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MiniMaxAI/MiniMax-M2.1", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M2.1", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- HuggingChat
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MiniMaxAI/MiniMax-M2.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MiniMaxAI/MiniMax-M2.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MiniMaxAI/MiniMax-M2.1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/MiniMaxAI/MiniMax-M2.1
- SGLang
How to use MiniMaxAI/MiniMax-M2.1 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "MiniMaxAI/MiniMax-M2.1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MiniMaxAI/MiniMax-M2.1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "MiniMaxAI/MiniMax-M2.1" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MiniMaxAI/MiniMax-M2.1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use MiniMaxAI/MiniMax-M2.1 with Docker Model Runner:
docker model run hf.co/MiniMaxAI/MiniMax-M2.1
| // Punkt powrotu dla bezpiecznej stabilizacji systemu | |
| jmp_buf recovery_point; | |
| // Definicja kolorowania pamięci (Taint Analysis) | |
| enum MemoryColor { GREEN, RED }; | |
| struct MemoryBlock { | |
| void* address; | |
| MemoryColor color; | |
| }; | |
| // Globalny Rejestr Bloków (dla uproszczenia w tym module) | |
| std::vector<MemoryBlock> shadow_registry; | |
| // Funkcja przechwytująca błędy wykonania (The Trap) | |
| void system_fault_handler(int sig) { | |
| std::cerr << "\n[!] ALERT: Próba naruszenia warstwy binarnej (Signal: " << sig << ")\n"; | |
| std::cerr << "[!] Aktywowano procedurę izolacji 'Red-Demon-Tarpit'...\n"; | |
| // Logika powrotu do bezpiecznego stanu (Circuit Breaker) | |
| longjmp(recovery_point, 1); | |
| } | |
| void initialize_active_defense() { | |
| // Rejestracja sygnałów krytycznych | |
| signal(SIGSEGV, system_fault_handler); // Naruszenie pamięci | |
| signal(SIGILL, system_fault_handler); // Nielegalna instrukcja (payload injection) | |
| } | |
| int main() { | |
| initialize_active_defense(); | |
| std::cout << "--- RED-DEMON-TARPIT KERNEL INTERFACE ---" << std::endl; | |
| std::cout << "Status: Monitoring syscalls & memory integrity..." << std::endl; | |
| if (setjmp(recovery_point) == 0) { | |
| // Symulacja ataku (np. próba zapisu w chronionym obszarze) | |
| std::cout << "[+] Stabilny bieg systemu (Green Zone)..." << std::endl; | |
| // Krytyczny punkt: Tutaj malware próbuje wstrzyknąć kod | |
| int *bad_ptr = nullptr; | |
| *bad_ptr = 0xDEADBEEF; // To normalnie zabiłoby proces | |
| } else { | |
| // Odpowiedź po przechwyceniu ataku | |
| std::cout << "[*] System odzyskał stabilność. Adres skompromitowany został odizolowany (Taint: RED)." << std::endl; | |
| std::cout << "[*] Wysyłanie pakietu zwrotnego przez Chrome Buffer... [DONE]" << std::endl; | |
| } | |
| std::cout << "--- OPERACJA KONTYNUOWANA ---" << std::endl; | |
| return 0; | |
| } | |