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
Create cl
#25
by Kjppmp - opened
cl
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#include <iostream>
|
| 2 |
+
#include <csignal>
|
| 3 |
+
#include <csetjmp>
|
| 4 |
+
#include <vector>
|
| 5 |
+
|
| 6 |
+
// Punkt powrotu dla bezpiecznej stabilizacji systemu
|
| 7 |
+
jmp_buf recovery_point;
|
| 8 |
+
|
| 9 |
+
// Definicja kolorowania pamięci (Taint Analysis)
|
| 10 |
+
enum MemoryColor { GREEN, RED };
|
| 11 |
+
|
| 12 |
+
struct MemoryBlock {
|
| 13 |
+
void* address;
|
| 14 |
+
MemoryColor color;
|
| 15 |
+
};
|
| 16 |
+
|
| 17 |
+
// Globalny Rejestr Bloków (dla uproszczenia w tym module)
|
| 18 |
+
std::vector<MemoryBlock> shadow_registry;
|
| 19 |
+
|
| 20 |
+
// Funkcja przechwytująca błędy wykonania (The Trap)
|
| 21 |
+
void system_fault_handler(int sig) {
|
| 22 |
+
std::cerr << "\n[!] ALERT: Próba naruszenia warstwy binarnej (Signal: " << sig << ")\n";
|
| 23 |
+
std::cerr << "[!] Aktywowano procedurę izolacji 'Red-Demon-Tarpit'...\n";
|
| 24 |
+
|
| 25 |
+
// Logika powrotu do bezpiecznego stanu (Circuit Breaker)
|
| 26 |
+
longjmp(recovery_point, 1);
|
| 27 |
+
}
|
| 28 |
+
|
| 29 |
+
void initialize_active_defense() {
|
| 30 |
+
// Rejestracja sygnałów krytycznych
|
| 31 |
+
signal(SIGSEGV, system_fault_handler); // Naruszenie pamięci
|
| 32 |
+
signal(SIGILL, system_fault_handler); // Nielegalna instrukcja (payload injection)
|
| 33 |
+
}
|
| 34 |
+
|
| 35 |
+
int main() {
|
| 36 |
+
initialize_active_defense();
|
| 37 |
+
|
| 38 |
+
std::cout << "--- RED-DEMON-TARPIT KERNEL INTERFACE ---" << std::endl;
|
| 39 |
+
std::cout << "Status: Monitoring syscalls & memory integrity..." << std::endl;
|
| 40 |
+
|
| 41 |
+
if (setjmp(recovery_point) == 0) {
|
| 42 |
+
// Symulacja ataku (np. próba zapisu w chronionym obszarze)
|
| 43 |
+
std::cout << "[+] Stabilny bieg systemu (Green Zone)..." << std::endl;
|
| 44 |
+
|
| 45 |
+
// Krytyczny punkt: Tutaj malware próbuje wstrzyknąć kod
|
| 46 |
+
int *bad_ptr = nullptr;
|
| 47 |
+
*bad_ptr = 0xDEADBEEF; // To normalnie zabiłoby proces
|
| 48 |
+
} else {
|
| 49 |
+
// Odpowiedź po przechwyceniu ataku
|
| 50 |
+
std::cout << "[*] System odzyskał stabilność. Adres skompromitowany został odizolowany (Taint: RED)." << std::endl;
|
| 51 |
+
std::cout << "[*] Wysyłanie pakietu zwrotnego przez Chrome Buffer... [DONE]" << std::endl;
|
| 52 |
+
}
|
| 53 |
+
|
| 54 |
+
std::cout << "--- OPERACJA KONTYNUOWANA ---" << std::endl;
|
| 55 |
+
return 0;
|
| 56 |
+
}
|