Instructions to use InternScience/MLExpert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InternScience/MLExpert with Transformers:

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

pipe = pipeline("text-generation", model="InternScience/MLExpert")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("InternScience/MLExpert")
model = AutoModelForMultimodalLM.from_pretrained("InternScience/MLExpert", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InternScience/MLExpert with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/InternScience/MLExpert

SGLang

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

Docker Model Runner
How to use InternScience/MLExpert with Docker Model Runner:
```
docker model run hf.co/InternScience/MLExpert
```

YoungDubby commited on 19 days ago

Commit

15498f2

verified ·

1 Parent(s): bf119de

Update README.md

Browse files

Update model links and usage commands to InternScience/M1

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ tags:
 # M1: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
-[🤗 Hugging Face](https://huggingface.co/YoungDubby/M1)
 **M1** is a 35B Mixture-of-Experts agentic model for autonomous machine learning engineering. It organizes experiments, writes and revises code, and improves solutions through sustained interaction with execution environments. Hierarchical agentic SFT develops general tool-use and domain-specific optimization skills, while **Windowed Interaction Reinforcement Learning (WIRL)** trains multi-turn decisions using feedback from completed experiments.
@@ -48,7 +48,7 @@ We also evaluate on NatureBench, following the ten-task Lite subset used in Fron
 ## Usage
-The commands below load `YoungDubby/M1` and serve an API endpoint at `http://localhost:8000/v1`.
 ### SGLang
@@ -64,7 +64,7 @@ uv pip install sglang
 ```shell
 python -m sglang.launch_server \
-    --model-path YoungDubby/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tp-size 2 \
@@ -77,7 +77,7 @@ python -m sglang.launch_server \
 ```shell
 python -m sglang.launch_server \
-    --model-path YoungDubby/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tp-size 2 \
@@ -100,7 +100,7 @@ uv pip install vllm --torch-backend=auto
 **Text Generation**
 ```shell
-vllm serve YoungDubby/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tensor-parallel-size 2 \
@@ -112,7 +112,7 @@ vllm serve YoungDubby/M1 \
 **Tool Calling**
 ```shell
-vllm serve YoungDubby/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tensor-parallel-size 2 \

 # M1: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
+[🤗 Hugging Face](https://huggingface.co/InternScience/M1)
 **M1** is a 35B Mixture-of-Experts agentic model for autonomous machine learning engineering. It organizes experiments, writes and revises code, and improves solutions through sustained interaction with execution environments. Hierarchical agentic SFT develops general tool-use and domain-specific optimization skills, while **Windowed Interaction Reinforcement Learning (WIRL)** trains multi-turn decisions using feedback from completed experiments.
 ## Usage
+The commands below load `InternScience/M1` and serve an API endpoint at `http://localhost:8000/v1`.
 ### SGLang
 ```shell
 python -m sglang.launch_server \
+    --model-path InternScience/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tp-size 2 \
 ```shell
 python -m sglang.launch_server \
+    --model-path InternScience/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tp-size 2 \
 **Text Generation**
 ```shell
+vllm serve InternScience/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tensor-parallel-size 2 \
 **Tool Calling**
 ```shell
+vllm serve InternScience/M1 \
     --host 127.0.0.1 \
     --port 8000 \
     --tensor-parallel-size 2 \