Instructions to use Can111/m1-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Can111/m1-32b with Transformers:

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

pipe = pipeline("text-generation", model="Can111/m1-32b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Can111/m1-32b")
model = AutoModelForCausalLM.from_pretrained("Can111/m1-32b")
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 Can111/m1-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Can111/m1-32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Can111/m1-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Can111/m1-32b

SGLang

How to use Can111/m1-32b 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 "Can111/m1-32b" \
    --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": "Can111/m1-32b",
		"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 "Can111/m1-32b" \
        --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": "Can111/m1-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Can111/m1-32b with Docker Model Runner:
```
docker model run hf.co/Can111/m1-32b
```

nielsr HF Staff commited on Apr 15, 2025

Commit

fb5d421

verified ·

1 Parent(s): e78d518

Add pipeline tag and link to code

Browse files

This PR adds the `pipeline_tag` to the model card, making it easier to find on the Hub. It also adds a link to the project's code repository.

Files changed (1) hide show

README.md +13 -10

README.md CHANGED Viewed

@@ -1,24 +1,27 @@
 ---
-library_name: transformers
 base_model: Qwen/Qwen2.5-32B-Instruct
-license: apache-2.0
 language:
-  - en
 tags:
-  - multi-agent systems
-  - multiagent-collaboration
-  - reasoning
-  - mathematics
-  - code
 model-index:
-  - name: m1-32b
-    results: []
 ---
 [Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning](https://arxiv.org/pdf/2504.09772)
 **M1-32B** is a 32B-parameter large language model fine-tuned from [Qwen2.5-32B-Instruct](https://arxiv.org/pdf/2412.15115) on the **M500** dataset—an interdisciplinary multi-agent collaborative reasoning dataset. M1-32B is optimized for improved reasoning, discussion, and decision-making in multi-agent systems (MAS), including frameworks such as [AgentVerse](https://github.com/OpenBMB/AgentVerse).
 ---
 ## 🚀 Key Features

 ---
 base_model: Qwen/Qwen2.5-32B-Instruct
 language:
+- en
+library_name: transformers
+license: apache-2.0
 tags:
+- multi-agent systems
+- multiagent-collaboration
+- reasoning
+- mathematics
+- code
 model-index:
+- name: m1-32b
+  results: []
+pipeline_tag: text-generation
 ---
 [Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning](https://arxiv.org/pdf/2504.09772)
 **M1-32B** is a 32B-parameter large language model fine-tuned from [Qwen2.5-32B-Instruct](https://arxiv.org/pdf/2412.15115) on the **M500** dataset—an interdisciplinary multi-agent collaborative reasoning dataset. M1-32B is optimized for improved reasoning, discussion, and decision-making in multi-agent systems (MAS), including frameworks such as [AgentVerse](https://github.com/OpenBMB/AgentVerse).
+Code: [https://github.com/jincan333/MAS-TTS](https://github.com/jincan333/MAS-TTS)
 ---
 ## 🚀 Key Features