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
```

More Benchmarks

by PSM24 - opened Nov 22, 2024

Discussion

PSM24

Nov 22, 2024

Can you add more benchmarks like MATH, MMLU, HumanEval, etc.?

Sniper

Nov 22, 2024

•

edited Nov 25, 2024

Thank you for your attention.

Our model has demonstrated preliminary feasibility in math-related tasks, primarily because data in this area is relatively easy to obtain, and the reward mechanisms are straightforward to design. However, our future focus will shift towards non-math tasks, particularly those involving open-ended questions. Therefore, we temporarily have no plans to evaluate the model on additional math benchmarks. However, we will soon present more experimental results and analyses on other tasks. Stay tuned for updates.

alpayariyak

Nov 22, 2024

In that case, why have the only reported benchmark be MGSM, a math benchmark?

Sniper

Nov 25, 2024

In that case, why have the only reported benchmark be MGSM, a math benchmark?

I apologize for any confusion caused by the incomplete response to the earlier question. The response has now been updated.

deleted

Nov 26, 2024

This comment has been hidden

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