Instructions to use togethercomputer/M1-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use togethercomputer/M1-3B with Transformers:

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

pipe = pipeline("text-generation", model="togethercomputer/M1-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("togethercomputer/M1-3B")
model = AutoModelForCausalLM.from_pretrained("togethercomputer/M1-3B")
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

vLLM

How to use togethercomputer/M1-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "togethercomputer/M1-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "togethercomputer/M1-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/togethercomputer/M1-3B

SGLang

How to use togethercomputer/M1-3B 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 "togethercomputer/M1-3B" \
    --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": "togethercomputer/M1-3B",
		"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 "togethercomputer/M1-3B" \
        --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": "togethercomputer/M1-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use togethercomputer/M1-3B with Docker Model Runner:
```
docker model run hf.co/togethercomputer/M1-3B
```

JunxiongWang commited on May 3, 2025

Commit

1bc26f6

verified ·

1 Parent(s): 4a11227

Create README.md

Browse files

Files changed (1) hide show

README.md +30 -0

README.md ADDED Viewed

	@@ -0,0 +1,30 @@

+---
+license: mit
+library_name: transformers
+pipeline_tag: text-generation
+---
+This is the model is trained using paper, [M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models](https://arxiv.org/abs/2504.10449).
+| **Model**                          | **AIME 2025** | **AIME 2024** | **MATH 500** | **AMC 2023** | **OlympiadBench** |
+|-----------------------------------|---------------|---------------|--------------|--------------|-------------------|
+| Qwen2.5-Math-7B-Instruct  (Transformer)        | –             | 13.3          | 79.8         | 50.6         | 40.7              |
+| rStar-Math-7B  (Transformer)                   | –             | 26.7          | 78.4         | 47.5         | 47.1              |
+| Eurus-2-7B-PRIME (Transformer)                 | –             | 26.7          | 79.2         | 57.8         | 42.1              |
+| Qwen2.5-7B-SimpleRL (Transformer)              | –             | 26.7          | 82.4         | 62.5         | 43.3              |
+| DeepSeek-R1-Distill-Qwen-1.5B (Transformer)    | 23.0          | 28.8          | 82.8         | 62.9         | 43.3              |
+| **M1-3B (Mamba Hybrid Models)**                | 23.5          | 28.5          | 84.0         | 62.8         | 47.3              |
+Code: https://github.com/jxiw/M1
+```
+@article{wang2025m1scalabletesttimecompute,
+  title={M1: Towards Scalable Test-Time Compute with Mamba Reasoning Models},
+  author={Junxiong Wang and Wen-Ding Li and Daniele Paliotta and Daniel Ritter and Alexander M. Rush and Tri Dao},
+  journal={arXiv preprint arXiv:2504.10449},
+  year={2025},
+  url={https://arxiv.org/abs/2504.10449},
+}