Instructions to use AIDC-AI/Marco-o1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIDC-AI/Marco-o1 with Transformers:

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

pipe = pipeline("text-generation", model="AIDC-AI/Marco-o1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIDC-AI/Marco-o1")
model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Marco-o1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AIDC-AI/Marco-o1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIDC-AI/Marco-o1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIDC-AI/Marco-o1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AIDC-AI/Marco-o1

SGLang

How to use AIDC-AI/Marco-o1 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 "AIDC-AI/Marco-o1" \
    --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": "AIDC-AI/Marco-o1",
		"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 "AIDC-AI/Marco-o1" \
        --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": "AIDC-AI/Marco-o1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AIDC-AI/Marco-o1 with Docker Model Runner:
```
docker model run hf.co/AIDC-AI/Marco-o1
```

explain why the performance differs between the En and Zh MGSM

by TonySilva423 - opened Nov 23, 2024

Discussion

TonySilva423

Nov 23, 2024

I really like the idea of mini-steps

Could you explain why the performance differs between the En and Zh MGSM? 64 vs. 32 tokens

Sniper

Nov 24, 2024

We believe that the performance difference between zh and en is due to the limitations of our current reward design. The current work's MCTS relies on the model's output probabilities, which might be strongly influenced by the higher baseline in English.
We need to emphasize that our MCTS results are not akin to sampling like PASS@K, but rather use the optimal reasoning path from the MCTS output as the result. Therefore, this result is significantly affected by the reward. In fact, we have observed that there are better outputs among other paths found during the MCTS.
We anticipate that this issue will be resolved later with the MCTS + reward model.

Sniper changed discussion status to closed Nov 29, 2024

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