Instructions to use AIDC-AI/Marco-o1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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 Settings
- 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
problems using this model in google colab
when I copy and paste this
"from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("AIDC-AI/Marco-o1")
model = AutoModelForCausalLM.from_pretrained("AIDC-AI/Marco-o1")"
in google colab, it doesn't load it completely because it tells me RAM used completely (despite using GPU) can you help me?
the problem is that google colab lets me connect to a GPU runtime but it doesn't use the GPU, can you help me?
What GPU are you using? Paid or Free?
@Matteo101 Yeah, I tried loading it directly like you did but it failed to engage the GPU. I even moved device to GPU but it kept using only CPU. I have not had time to properly review the model implementation or official documentation to know why. For now, I got it to load by reducing the precision to float 16. It is now using about 13GB of VRAM:
class ModelWrapper:
def __init__(self, model_name):
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# Load model with half-precision if supported, or use device_map for efficient placement
try:
self.model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16 if torch.cuda.is_available() else None,
device_map="auto"
)
except Exception as e:
print(f"Error loading model: {e}")
raise
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
# Enable gradient checkpointing for large models
self.model.gradient_checkpointing_enable()
# Debug: Check if model is on GPU
print(f"Model loaded to device: {next(self.model.parameters()).device}")
def generate_text(self, prompt, max_length=100, num_return_sequences=1):
inputs = self.tokenizer(prompt, return_tensors="pt")
inputs = {key: value.to(self.device) for key, value in inputs.items()} # Move inputs to GPU
outputs = self.model.generate(
**inputs, max_length=max_length, num_return_sequences=num_return_sequences
)
generated_texts = [
self.tokenizer.decode(output, skip_special_tokens=True) for output in outputs
]
return generated_texts
Results:
Model loaded to device: cuda:0
Generated Text 1:
Once upon a time, in a land far, far away, there was a kingdom with a unique rule: the king could only be chosen if he had at least one sibling. This rule was based on an ancient prophecy that stated, "The kingdom
