Instructions to use internlm/Intern-S2-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use internlm/Intern-S2-Preview with Transformers:

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

pipe = pipeline("image-text-to-text", model="internlm/Intern-S2-Preview", 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 AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("internlm/Intern-S2-Preview", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use internlm/Intern-S2-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "internlm/Intern-S2-Preview"
# 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-S2-Preview",
		"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-S2-Preview

SGLang

How to use internlm/Intern-S2-Preview 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-S2-Preview" \
    --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-S2-Preview",
		"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-S2-Preview" \
        --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-S2-Preview",
		"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-S2-Preview with Docker Model Runner:
```
docker model run hf.co/internlm/Intern-S2-Preview
```

Add evaluation results (HLE, HMMT, MMLU-Pro, SWE-bench Verified)

by SaylorTwift HF Staff - opened about 15 hours ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+33

-0

YAML Metadata Error:Invalid content in Eval Result file .eval_results/hle.yaml

Check out the documentation for more information.

Show details

Task ID "hle" does not match any task in dataset "cais/hle". Available: none

Files changed (4) hide show

.eval_results/hle.yaml +9 -0
.eval_results/hmmt_feb_2026.yaml +8 -0
.eval_results/mmlu_pro.yaml +8 -0
.eval_results/swe_bench_verified.yaml +8 -0

.eval_results/hle.yaml ADDED Viewed

	@@ -0,0 +1,9 @@

+- dataset:
+    id: cais/hle
+    task_id: hle
+  value: 21.94
+  date: '2026-05-12'
+  source:
+    url: https://huggingface.co/internlm/Intern-S2-Preview
+    name: Model Card
+  notes: "Text only"

.eval_results/hmmt_feb_2026.yaml ADDED Viewed

	@@ -0,0 +1,8 @@

+- dataset:
+    id: MathArena/hmmt_feb_2026
+    task_id: MathArena/hmmt_feb_2026
+  value: 87.31
+  date: '2026-05-12'
+  source:
+    url: https://huggingface.co/internlm/Intern-S2-Preview
+    name: Model Card

.eval_results/mmlu_pro.yaml ADDED Viewed

	@@ -0,0 +1,8 @@

+- dataset:
+    id: TIGER-Lab/MMLU-Pro
+    task_id: mmlu_pro
+  value: 88.0
+  date: '2026-05-12'
+  source:
+    url: https://huggingface.co/internlm/Intern-S2-Preview
+    name: Model Card

.eval_results/swe_bench_verified.yaml ADDED Viewed

	@@ -0,0 +1,8 @@

+- dataset:
+    id: SWE-bench/SWE-bench_Verified
+    task_id: swe_bench_%_resolved
+  value: 64.0
+  date: '2026-05-12'
+  source:
+    url: https://huggingface.co/internlm/Intern-S2-Preview
+    name: Model Card