Instructions to use xiaomi-research/SpatioLM-Perception-InternVL3.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xiaomi-research/SpatioLM-Perception-InternVL3.5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="xiaomi-research/SpatioLM-Perception-InternVL3.5")
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 AutoModel
model = AutoModel.from_pretrained("xiaomi-research/SpatioLM-Perception-InternVL3.5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xiaomi-research/SpatioLM-Perception-InternVL3.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xiaomi-research/SpatioLM-Perception-InternVL3.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xiaomi-research/SpatioLM-Perception-InternVL3.5",
		"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/xiaomi-research/SpatioLM-Perception-InternVL3.5

SGLang

How to use xiaomi-research/SpatioLM-Perception-InternVL3.5 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 "xiaomi-research/SpatioLM-Perception-InternVL3.5" \
    --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": "xiaomi-research/SpatioLM-Perception-InternVL3.5",
		"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 "xiaomi-research/SpatioLM-Perception-InternVL3.5" \
        --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": "xiaomi-research/SpatioLM-Perception-InternVL3.5",
		"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 xiaomi-research/SpatioLM-Perception-InternVL3.5 with Docker Model Runner:
```
docker model run hf.co/xiaomi-research/SpatioLM-Perception-InternVL3.5
```

SpatioLM-Perception-InternVL3.5 / config.json

edatai

Upload model checkpoint

5e7835e verified 3 days ago

Raw

History Blame Contribute Delete

7.5 kB

	{
	"architectures": [
	"InternVL3RChatModel"
	],
	"downsample_ratio": 0.5,
	"dtype": "bfloat16",
	"dynamic_image_size": true,
	"eos_token_id": 151645,
	"force_image_size": 448,
	"hidden_size": 4096,
	"keys_to_ignore_at_inference": [
	"past_key_values"
	],
	"llm_config": {
	"architectures": [
	"Qwen3ForV3RCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 151643,
	"debug": false,
	"dtype": "bfloat16",
	"eos_token_id": 151645,
	"ep_size": 1,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 40960,
	"max_window_layers": 36,
	"micro_forward": false,
	"model_type": "qwen3_v3r",
	"num_attention_heads": 32,
	"num_hidden_layers": 36,
	"num_key_value_heads": 8,
	"pad_token_id": 151643,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000,
	"skip_checkpoint": false,
	"sliding_window": null,
	"use_cache": false,
	"use_deepep": false,
	"use_sliding_window": false,
	"vision3r_head_dim": 32,
	"vision3r_intermediate_size": 1024,
	"vision3r_layer_ids": [
	4,
	8,
	12,
	16,
	20,
	24
	],
	"vision3r_num_attention_heads": 16,
	"vocab_size": 151936
	},
	"max_dynamic_patch": 12,
	"min_dynamic_patch": 1,
	"model_type": "internvl_chat",
	"output_attentions": false,
	"pad2square": false,
	"pad_token_id": 151643,
	"ps_version": "v2",
	"select_layer": 18,
	"template": "internvl2_5",
	"tie_word_embeddings": false,
	"transformers_version": null,
	"use_backbone_lora": 0,
	"use_llm_lora": 0,
	"use_thumbnail": true,
	"vision_condition_config": null,
	"vision_config": {
	"architectures": [
	"InternVisionModel"
	],
	"attention_dropout": 0.0,
	"drop_path_rate": 0.1,
	"dropout": 0.0,
	"dtype": "bfloat16",
	"hidden_act": "gelu",
	"hidden_size": 1024,
	"image_size": 448,
	"initializer_factor": 1.0,
	"initializer_range": 0.02,
	"intermediate_size": 4096,
	"layer_norm_eps": 1e-06,
	"model_type": "intern_vit_6b",
	"norm_type": "layer_norm",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 24,
	"pad_token_id": 151643,
	"patch_size": 14,
	"qk_normalization": false,
	"qkv_bias": true,
	"use_fa3": false,
	"use_flash_attn": true
	},
	"vision_dpt_config": {
	"_name_or_path": "",
	"add_cross_attention": false,
	"architectures": null,
	"bad_words_ids": null,
	"begin_suppress_tokens": null,
	"bos_token_id": null,
	"chunk_size_feed_forward": 0,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"diversity_penalty": 0.0,
	"do_sample": false,
	"dpt_config": {
	"_name_or_path": "",
	"add_cross_attention": false,
	"alt_start": 8,
	"architectures": [
	"DA3Model"
	],
	"backbone_name": "vitl",
	"bad_words_ids": null,
	"begin_suppress_tokens": null,
	"bos_token_id": null,
	"camera_dec_dim_in": 2048,
	"camera_enc_dim_out": 1024,
	"cat_token": true,
	"chunk_size_feed_forward": 0,
	"cross_attention_hidden_size": null,
	"decoder_start_token_id": null,
	"depth_dim_in": 4096,
	"depth_dim_out": 2,
	"depth_features": 256,
	"depth_out_channels": [
	256,
	512,
	1024,
	1024
	],
	"diversity_penalty": 0.0,
	"do_sample": false,
	"dtype": null,
	"early_stopping": false,
	"encoder_no_repeat_ngram_size": 0,
	"eos_token_id": null,
	"exponential_decay_length_penalty": null,
	"finetuning_task": null,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"hidden_size": 4096,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"image_size": 518,
	"is_decoder": false,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"length_penalty": 1.0,
	"max_length": 20,
	"min_length": 0,
	"model_type": "depth_anything_3",
	"no_repeat_ngram_size": 0,
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_return_sequences": 1,
	"out_layers": [
	11,
	15,
	19,
	23
	],
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": 151643,
	"patch_size": 14,
	"prefix": null,
	"problem_type": null,
	"pruned_heads": {},
	"qknorm_start": 8,
	"remove_invalid_values": false,
	"repetition_penalty": 1.0,
	"return_dict": true,
	"return_dict_in_generate": false,
	"rope_start": 8,
	"sep_token_id": null,
	"suppress_tokens": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torchscript": false,
	"transformers_version": "4.57.1",
	"typical_p": 1.0,
	"use_bfloat16": false
	},
	"dtype": "float32",
	"early_stopping": false,
	"encoder_no_repeat_ngram_size": 0,
	"eos_token_id": null,
	"exponential_decay_length_penalty": null,
	"finetuning_task": null,
	"forced_bos_token_id": null,
	"forced_eos_token_id": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"is_decoder": false,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_ids": [
	0,
	2,
	4,
	6
	],
	"length_penalty": 1.0,
	"max_length": 20,
	"min_length": 0,
	"no_repeat_ngram_size": 0,
	"num_beam_groups": 1,
	"num_beams": 1,
	"num_return_sequences": 1,
	"output_attentions": false,
	"output_hidden_states": false,
	"output_scores": false,
	"pad_token_id": null,
	"prefix": null,
	"problem_type": null,
	"pruned_heads": {},
	"remove_invalid_values": false,
	"repetition_penalty": 1.0,
	"return_dict": true,
	"return_dict_in_generate": false,
	"sep_token_id": null,
	"suppress_tokens": null,
	"task_specific_params": null,
	"temperature": 1.0,
	"tf_legacy_loss": false,
	"tie_encoder_decoder": false,
	"tie_word_embeddings": true,
	"tokenizer_class": null,
	"top_k": 50,
	"top_p": 1.0,
	"torchscript": false,
	"transformers_version": null,
	"typical_p": 1.0,
	"use_bfloat16": false
	}
	}