Instructions to use OpenGVLab/InternVL3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenGVLab/InternVL3-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3-8B", 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 AutoModel
model = AutoModel.from_pretrained("OpenGVLab/InternVL3-8B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenGVLab/InternVL3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenGVLab/InternVL3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenGVLab/InternVL3-8B",
		"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/OpenGVLab/InternVL3-8B

SGLang

How to use OpenGVLab/InternVL3-8B 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 "OpenGVLab/InternVL3-8B" \
    --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": "OpenGVLab/InternVL3-8B",
		"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 "OpenGVLab/InternVL3-8B" \
        --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": "OpenGVLab/InternVL3-8B",
		"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 OpenGVLab/InternVL3-8B with Docker Model Runner:
```
docker model run hf.co/OpenGVLab/InternVL3-8B
```

InternVL3-8B latency is too much

by skywalker-9 - opened Apr 24, 2025

Discussion

skywalker-9

Apr 24, 2025

•

edited Apr 24, 2025

InternVL3-8B latency is too much compared to InternVL2-8B
Per frame inferencing for selecting best frames based on the output_scores for a specific prompt is taking around 3 to 4 seconds which is much higher than InternVL2-8B

Are there any parameters that needs to be set explicitly ?

self.model.config.llm_config: Qwen2Config {
"_attn_implementation_autoset": true,
"_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 70,
"model_type": "qwen2",
"moe_config": null,
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 2.0,
"rope_type": "dynamic",
"type": "dynamic"
},
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"use_bfloat16": true,
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151674
}

self.model.config.vision_config: InternVisionConfig {
"_attn_implementation_autoset": true,
"_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
"architectures": [
"InternVisionModel"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
"AutoModel": "modeling_intern_vit.InternVisionModel"
},
"capacity_factor": 1.2,
"drop_path_rate": 0.1,
"dropout": 0.0,
"eval_capacity_factor": 1.4,
"hidden_act": "gelu",
"hidden_size": 1024,
"image_size": 448,
"initializer_factor": 0.1,
"initializer_range": 1e-10,
"intermediate_size": 4096,
"laux_allreduce": "all_nodes",
"layer_norm_eps": 1e-06,
"model_type": "intern_vit_6b",
"moe_coeff_ratio": 0.5,
"moe_intermediate_size": 768,
"moe_output_scale": 4.0,
"noisy_gate_policy": "RSample_before",
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_channels": 3,
"num_experts": 8,
"num_hidden_layers": 24,
"num_routed_experts": 4,
"num_shared_experts": 4,
"patch_size": 14,
"qk_normalization": false,
"qkv_bias": true,
"shared_expert_intermediate_size": 3072,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"use_bfloat16": true,
"use_flash_attn": true,
"use_moe": false,
"use_residual": true,
"use_rts": false,
"use_weighted_residual": false
}

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment