Instructions to use internlm/Intern-S1-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/Intern-S1-Pro with Transformers:

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

pipe = pipeline("image-text-to-text", model="internlm/Intern-S1-Pro", trust_remote_code=True)
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)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("internlm/Intern-S1-Pro", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use internlm/Intern-S1-Pro with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/Intern-S1-Pro"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "internlm/Intern-S1-Pro",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/internlm/Intern-S1-Pro

SGLang

How to use internlm/Intern-S1-Pro 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 "internlm/Intern-S1-Pro" \
    --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": "internlm/Intern-S1-Pro",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "internlm/Intern-S1-Pro" \
        --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": "internlm/Intern-S1-Pro",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use internlm/Intern-S1-Pro with Docker Model Runner:
```
docker model run hf.co/internlm/Intern-S1-Pro
```

QipengGuo

unsubscribe commited on Feb 12

Commit

82d0f52

1 Parent(s): 1ba4154

Update sglang info (#10)

Browse files

- Update sglang info (9d2505c1567ca6132027b181c22f8151420a1289)

Co-authored-by: lmdeploy <unsubscribe@users.noreply.huggingface.co>

Files changed (1) hide show

deployment_guide.md +3 -1

deployment_guide.md CHANGED Viewed

@@ -1,6 +1,6 @@
 # Intern-S1-Pro Deployment Guide
-The Intern-S1-Pro release is a 1T parameter model stored in FP8 format. Deployment requires at least two 8-GPU H200 nodes, with either of the following configurations:
 - Tensor Parallelism (TP)
 - Data Parallelism (DP) + Expert Parallelism (EP)
@@ -126,6 +126,8 @@ vllm serve internlm/Intern-S1-Pro \
 ## SGLang
 - Tensor Parallelism + Expert Parallelism
 ```bash

 # Intern-S1-Pro Deployment Guide
+The Intern-S1-Pro release is a 1T parameter model stored in FP8 format. Deployment requires at least **two 8-GPU H200** nodes, with either of the following configurations:
 - Tensor Parallelism (TP)
 - Data Parallelism (DP) + Expert Parallelism (EP)
 ## SGLang
+You can use the docker image `lmsysorg/sglang:dev` to deploy. Refer to [using-docker](https://docs.sglang.io/get_started/install.html#method-3-using-docker) for more.
 - Tensor Parallelism + Expert Parallelism
 ```bash