Image-Text-to-Text
Transformers
Safetensors
llava_onevision2_5
text-generation
multimodal
video-understanding
streaming
llava-onevision
conversational
custom_code
Instructions to use lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct", 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)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct", "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/lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct
- SGLang
How to use lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct 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 "lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct" \ --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": "lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct", "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 "lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct" \ --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": "lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct", "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 lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct with Docker Model Runner:
docker model run hf.co/lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct
Download config.json from lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct: direct link, hf CLI and curl.
- Browser
- Download file 3.7 kB
-
https://huggingface.co/lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct/resolve/main/config.json
- Command line
-
hf download hf://lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct/config.json
-
curl -L -o config.json https://huggingface.co/lmms-lab-encoder/LLaVA-OneVision-2.5-4B-Instruct/resolve/main/config.json
3.7 kB
| { | |
| "architectures": [ | |
| "LlavaOnevision2_5ForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_llava_onevision2_5.LlavaOnevision2_5Config", | |
| "AutoModelForCausalLM": "modeling_llava_onevision2_5.LlavaOnevision2_5ForConditionalGeneration", | |
| "AutoModel": "modeling_llava_onevision2_5.LlavaOnevision2_5ForConditionalGeneration", | |
| "AutoModelForImageTextToText": "modeling_llava_onevision2_5.LlavaOnevision2_5ForConditionalGeneration", | |
| "AutoProcessor": "processing_llava_onevision2_5.LlavaOnevision2_5Processor", | |
| "AutoVideoProcessor": "video_processing_llava_onevision2_5.LlavaOnevision2_5VideoProcessor" | |
| }, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "image_token_id": 248056, | |
| "model_type": "llava_onevision2_5", | |
| "pad_token_id": null, | |
| "text_config": { | |
| "_name_or_path": "", | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "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_conv_kernel_dim": 4, | |
| "linear_key_head_dim": 128, | |
| "linear_num_key_heads": 16, | |
| "linear_num_value_heads": 32, | |
| "linear_value_head_dim": 128, | |
| "mamba_ssm_dtype": "float32", | |
| "max_position_embeddings": 262144, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_5_text", | |
| "mtp_num_hidden_layers": 1, | |
| "mtp_use_dedicated_embeddings": false, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 11, | |
| 11, | |
| 10 | |
| ], | |
| "partial_rotary_factor": 0.25, | |
| "rope_theta": 10000000, | |
| "rope_type": "default" | |
| }, | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "vocab_size": 248320 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.7.0.dev0", | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "frame_windows_size": 1, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-06, | |
| "layer_norm_type": "layer_norm", | |
| "model_type": "onevision_encoder", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "out_hidden_size": 2560, | |
| "patch_size": 16, | |
| "rope_theta": 10000.0, | |
| "spatial_merge_size": 3, | |
| "temporal_patch_size": 1, | |
| "text_hidden_size": 2560, | |
| "tokens_per_second": 1, | |
| "use_head": false | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053 | |
| } |