Instructions to use PrimeIntellect/minimax-m2-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PrimeIntellect/minimax-m2-tiny with Transformers:

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

pipe = pipeline("text-generation", model="PrimeIntellect/minimax-m2-tiny")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PrimeIntellect/minimax-m2-tiny")
model = AutoModelForCausalLM.from_pretrained("PrimeIntellect/minimax-m2-tiny")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PrimeIntellect/minimax-m2-tiny with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PrimeIntellect/minimax-m2-tiny"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PrimeIntellect/minimax-m2-tiny",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PrimeIntellect/minimax-m2-tiny

SGLang

How to use PrimeIntellect/minimax-m2-tiny 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 "PrimeIntellect/minimax-m2-tiny" \
    --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": "PrimeIntellect/minimax-m2-tiny",
		"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 "PrimeIntellect/minimax-m2-tiny" \
        --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": "PrimeIntellect/minimax-m2-tiny",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PrimeIntellect/minimax-m2-tiny with Docker Model Runner:
```
docker model run hf.co/PrimeIntellect/minimax-m2-tiny
```

minimax-m2-tiny / README.md

samsja

Upload folder using huggingface_hub

ad6b392 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

1.22 kB

	---
	license: apache-2.0
	tags:
	- prime-rl
	- moe
	- test-model
	library_name: transformers
	---

	<div align="center">
	<img src="/static-proxy?url=https%3A%2F%2Fcdn-avatars.huggingface.co%2Fv1%2Fproduction%2Fuploads%2F61e020e4a343274bb132e138%2FH2mcdPRWtl4iKLd-OYYBc.jpeg%26quot%3B%3C%2Fspan%3E width="200"/>
	</div>

	# minimax-m2-tiny

	A small (~252M parameter) MiniMax M2 MoE model for testing only. It is generally compatible with vLLM and HuggingFace Transformers but is meant to be used with [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl).

	This model has random weights (no SFT warmup yet due to a chat template tokenization issue with MiniMax's tokenizer).

	## Quick Start

	```bash
	uv run rl @ configs/ci/integration/rl_moe/minimax_m2.toml
	```

	See the [Testing MoE at Small Scale](https://github.com/PrimeIntellect-ai/prime-rl/blob/main/docs/testing-moe-at-small-scale.md) guide for full instructions.

	## Model Details

	\| Parameter \| Value \|
	\|-----------\|-------\|
	\| Hidden size \| 512 \|
	\| Layers \| 12 \|
	\| Experts \| 8 \|
	\| Active experts \| 4 \|
	\| Parameters \| ~252M \|

	## Links

	- [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) - RL training framework
	- [PrimeIntellect](https://www.primeintellect.ai/) - Building infrastructure for decentralized AI