Image-Text-to-Text
Transformers
Safetensors
multilingual
internvl_chat
feature-extraction
internvl
custom_code
conversational
Instructions to use OpenGVLab/InternVL3_5-30B-A3B-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/InternVL3_5-30B-A3B-Flash with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="OpenGVLab/InternVL3_5-30B-A3B-Flash", 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_5-30B-A3B-Flash", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use OpenGVLab/InternVL3_5-30B-A3B-Flash with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenGVLab/InternVL3_5-30B-A3B-Flash" # 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_5-30B-A3B-Flash", "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_5-30B-A3B-Flash
- SGLang
How to use OpenGVLab/InternVL3_5-30B-A3B-Flash 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_5-30B-A3B-Flash" \ --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_5-30B-A3B-Flash", "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_5-30B-A3B-Flash" \ --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_5-30B-A3B-Flash", "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_5-30B-A3B-Flash with Docker Model Runner:
docker model run hf.co/OpenGVLab/InternVL3_5-30B-A3B-Flash
| { | |
| "architectures": [ | |
| "InternVLChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", | |
| "AutoModel": "modeling_internvl_chat.InternVLChatModel", | |
| "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": true, | |
| "eos_token_id": 151645, | |
| "force_image_size": 448, | |
| "flash_mode": true, | |
| "flash_relative_threshold": 0.1, | |
| "flash_absolute_threshold": 0.5, | |
| "llm_config": { | |
| "_name_or_path": "/root/codespace/checkpoints/Qwen3-30B-A3B", | |
| "architectures": [ | |
| "Qwen3MoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "decoder_sparse_step": 1, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 48, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_moe", | |
| "moe_intermediate_size": 768, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 4, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "max_dynamic_patch": 12, | |
| "min_dynamic_patch": 1, | |
| "model_type": "internvl_chat", | |
| "pad2square": false, | |
| "pad_token_id": 151643, | |
| "ps_version": "v2", | |
| "select_layer": -1, | |
| "template": "internvl2_5", | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": null, | |
| "use_backbone_lora": 0, | |
| "use_llm_lora": 0, | |
| "use_thumbnail": true, | |
| "vision_config": { | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", | |
| "AutoModel": "modeling_intern_vit.InternVisionModel" | |
| }, | |
| "drop_path_rate": 0.1, | |
| "dropout": 0.0, | |
| "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, | |
| "patch_size": 14, | |
| "qk_normalization": false, | |
| "qkv_bias": true, | |
| "torch_dtype": "bfloat16", | |
| "use_flash_attn": true | |
| } | |
| } |