You can deploy this model and start earning money today!

luhkronn/
MiniMax-M2

Name: MiniMax-M2
Rating: 2.5 (8 reviews)

Views

No views yet

MiniMax-M2 Model Repository

This is the official MiniMax-M2 model repository containing a 230B parameter MoE model with 10B active parameters, optimized for coding and agentic workflows.

Model Information

Model Type: Mixture of Experts (MoE)
Total Parameters: 230B
Active Parameters: 10B
Architecture: Transformer-based MoE
License: Modified MIT
Pipeline Tag: text-generation

Usage

This model can be used with various inference frameworks:

Transformers

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("your-username/MiniMax-M2")
tokenizer = AutoTokenizer.from_pretrained("your-username/MiniMax-M2")

vLLM

python

from vllm import LLM, SamplingParams

llm = LLM(model="your-username/MiniMax-M2")

SGLang

python

from sglang import function, system, user, assistant, gen, select

@function
def multi_turn_question(s, question):
    s += system("You are a helpful assistant.")
    s += user(question)
    s += assistant(gen("answer", max_tokens=256))
    return s["answer"]

Model Details

Context Length: 128K tokens
Thinking Format: Uses <think>...</think> tags for reasoning
Recommended Parameters:
- Temperature: 1.0
- Top-p: 0.95
- Top-k: 40

Deployment Guides

See the docs/ directory for detailed deployment guides:

License

This model is released under the Modified MIT License. See the license file for details.

luhkronn/MiniMax-M2

MiniMax-M2 Model Repository

Model Information

Usage

Transformers

vLLM

SGLang

Model Details

Deployment Guides

License

luhkronn/
MiniMax-M2