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
```

Intern-S2-Preview / config.json

haijunlv

upload1

de4f18d verified 1 day ago

raw

history blame contribute delete

4.42 kB

	{
	"model_type": "intern_s2_preview",
	"architectures": [
	"InternS2PreviewForConditionalGeneration"
	],
	"transformers_version": "5.2.0",
	"auto_map": {
	"AutoConfig": "configuration_interns2_preview.InternS2PreviewConfig",
	"AutoModelForCausalLM": "modeling_interns2_preview.InternS2PreviewForCausalLM",
	"AutoModel": "modeling_interns2_preview.InternS2PreviewModel",
	"AutoModelForImageTextToText": "modeling_interns2_preview.InternS2PreviewForConditionalGeneration",
	"AutoModelForMultimodalLM": "modeling_interns2_preview.InternS2PreviewForConditionalGeneration"
	},
	"image_token_id": 248056,
	"text_config": {
	"model_type": "qwen3_5_moe_text",
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"moe_intermediate_size": 512,
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 16,
	"num_experts": 256,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 40,
	"num_key_value_heads": 2,
	"rms_norm_eps": 1e-06,
	"router_aux_loss_coef": 0.001,
	"shared_expert_intermediate_size": 512,
	"use_cache": true,
	"vocab_size": 251392,
	"mamba_ssm_dtype": "float32",
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"rope_type": "default",
	"rope_theta": 10000000,
	"partial_rotary_factor": 0.25
	},
	"pad_token_id": null,
	"bos_token_id": null,
	"tie_word_embeddings": false,
	"output_router_logits": false,
	"partial_rotary_factor": 0.25
	},
	"tie_word_embeddings": false,
	"video_token_id": 248057,
	"vision_config": {
	"model_type": "intern_s2_preview",
	"deepstack_visual_indexes": [],
	"depth": 27,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4304,
	"num_heads": 16,
	"num_position_embeddings": 2304,
	"out_hidden_size": 2048,
	"patch_size": 16,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 248054,
	"vision_start_token_id": 248053,
	"ts_config": {
	"model_type": "interns2_preview_time_series",
	"auto_map": {
	"AutoConfig": "configuration_interns2_preview.InternS2PreviewTimeSeriesConfig",
	"AutoModel": "modeling_interns2_preview.InternS2PreviewTimeSeriesModel"
	},
	"activation_dropout": 0.0,
	"activation_function": "gelu",
	"attention_dropout": 0.0,
	"d_model": 768,
	"dropout": 0.0,
	"encoder_attention_heads": 8,
	"encoder_ffn_dim": 3072,
	"encoder_layerdrop": 0.0,
	"encoder_layers": 17,
	"max_source_positions": 1500,
	"num_mel_bins": 80,
	"out_hidden_size": 2048,
	"scale_embedding": false,
	"ts_adapt_in_dim": 256,
	"ts_adapt_out_dim": 1024,
	"ts_hidden_dim": 1024
	},
	"ts_token_id": 248093,
	"ts_start_id": 248091,
	"ts_end_id": 248092
	}