Instructions to use MiniMaxAI/MiniMax-M1-80k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MiniMaxAI/MiniMax-M1-80k with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MiniMaxAI/MiniMax-M1-80k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("MiniMaxAI/MiniMax-M1-80k", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MiniMaxAI/MiniMax-M1-80k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MiniMaxAI/MiniMax-M1-80k"
# 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-M1-80k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MiniMaxAI/MiniMax-M1-80k

SGLang

How to use MiniMaxAI/MiniMax-M1-80k 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-M1-80k" \
    --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-M1-80k",
		"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-M1-80k" \
        --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-M1-80k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MiniMaxAI/MiniMax-M1-80k with Docker Model Runner:
```
docker model run hf.co/MiniMaxAI/MiniMax-M1-80k
```

Was the 7.5T Token Continual Pre-Training Performed on the Instruction-Tuned Model or the Base PLM?

#10

by Jinhwan - opened Jun 23, 2025

Discussion

Jinhwan

Jun 23, 2025

Hello, and thank you for your impressive work on the MiniMax-M1 project!

In the paper, it is mentioned that a 7.5T token continual pre-training (CPT) was performed based on the MiniMax-Text-01 model.

To clarify, was this CPT applied to the instruction-tuned model (MiniMax-Text-01 Instruction), or was it conducted on the base pretrained language model (MiniMax-Text-01 PLM) before any instruction tuning?
(Here, “MiniMax-Text-01 Instruction” and “MiniMax-Text-01 PLM” are just placeholder terms for clarity.)

Understanding this detail would help clarify how CPT fits into the overall training pipeline and what its intended role is.

Thank you in advance!

sriting

MiniMax org Jun 23, 2025

Hi @Jinhwan . It was on the base PLM. Hope that helps!

Jinhwan

Jun 24, 2025

Thank you for the clarification! @sriting
I have a follow-up question regarding the implementation details.

Is it correct that there are no special tokens such as and to explicitly mark reasoning paths (i.e., Chain-of-Thought segments) in the model output?

I ask this because some recent models (e.g., Qwen3, DeepSeek-MoE) adopt such tags to separate reasoning and final answers. I’m curious whether MiniMax-M1 internally uses similar markers during SFT or RL training, or if reasoning is handled purely implicitly through instruction and response formatting.

Thanks again for your time and support!

sori05

Jun 26, 2025

Bro it is not working now

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment