--- title: SmolVLM2-500M-Video-Instruct canonical_url: "https://www.modelscope.cn/models/HuggingFaceTB/SmolVLM2-500M-Video-Instruct" md_url: "https://www.modelscope.cn/models/HuggingFaceTB/SmolVLM2-500M-Video-Instruct.md" repository: HuggingFaceTB/SmolVLM2-500M-Video-Instruct last_updated: 2025-02-22 license: apache-2.0 model_type: - smolvlm architectures: - SmolVLMForConditionalGeneration base_model: - HuggingFaceTB/SmolVLM-500M-Instruct base_model_relation: finetune parameters: 507.5M tensor_type: - F32 library_name: - pytorch - transformer - onnx - safetensors frameworks: - pytorch language: - en inference_backends: - "deploy_task vlm/text/emb" - "vllm 0.9.2" downloads: 3657 stars: 2 --- # SmolVLM2-500M-Video-Instruct > SmolVLM2-500M-Video-Instruct - HuggingFaceTB 在 ModelScope 开源的模型。SmolVLM2-500M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering… HuggingFaceTB/SmolVLM2-500M-Video-Instruct 是 ModelScope 魔搭社区上的 507.5M 参数机器学习模型，采用 apache-2.0 许可，基于 HuggingFaceTB/SmolVLM-500M-Instruct 构建，可用 deploy_task vlm/text/emb、vllm 0.9.2 部署。 - **Repository**: HuggingFaceTB/SmolVLM2-500M-Video-Instruct - **License**: apache-2.0 - **Parameters**: 507.5M - **Base model**: HuggingFaceTB/SmolVLM-500M-Instruct - **Inference backends**: deploy_task vlm/text/emb, vllm 0.9.2 - **Downloads**: 3657 - **Stars**: 2 - **Last updated**: 2025-02-22 Source: https://www.modelscope.cn/models/HuggingFaceTB/SmolVLM2-500M-Video-Instruct --- Image description # SmolVLM2-500M-Video SmolVLM2-500M-Video is a lightweight multimodal model designed to analyze video content. The model processes videos, images, and text inputs to generate text outputs - whether answering questions about media files, comparing visual content, or transcribing text from images. Despite its compact size, requiring only 1.8GB of GPU RAM for video inference, it delivers robust performance on complex multimodal tasks. This efficiency makes it particularly well-suited for on-device applications where computational resources may be limited. ## Model Summary - **Developed by:** Hugging Face 🤗 - **Model type:** Multi-modal model (image/multi-image/video/text) - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Architecture:** Based on [Idefics3](https://huggingface.co/HuggingFaceM4/Idefics3-8B-Llama3) (see technical summary) ## Resources - **Demo:** [Video Highlight Generator](https://huggingface.co/spaces/HuggingFaceTB/SmolVLM2-HighlightGenerator) - **Blog:** [Blog post](https://huggingface.co/blog/smolvlm2) ## Uses SmolVLM2 can be used for inference on multimodal (video / image / text) tasks where the input consists of text queries along with video or one or more images. Text and media files can be interleaved arbitrarily, enabling tasks like captioning, visual question answering, and storytelling based on visual content. The model does not support image or video generation. To fine-tune SmolVLM2 on a specific task, you can follow [the fine-tuning tutorial](https://github.com/huggingface/smollm/blob/main/vision/finetuning/Smol_VLM_FT.ipynb). ## Evaluation We evaluated the performance of the SmolVLM2 family on the following scientific benchmarks: | Size | Video-MME | MLVU | MVBench | |----------|-----------------|----------|---------------| | 2.2B | 52.1 | 55.2 | 46.27 | | 500M | 42.2 | 47.3 | 39.73 | | 256M | 33.7 | 40.6 | 32.7 | ### How to get started You can use transformers to load, infer and fine-tune SmolVLM. Make sure you have num2words, flash-attn and latest transformers installed. You can load the model as follows. ```python from transformers import AutoProcessor, AutoModelForImageTextToText model_path = "HuggingFaceTB/SmolVLM2-500M-Video-Instruct" processor = AutoProcessor.from_pretrained(model_path) model = AutoModelForImageTextToText.from_pretrained( model_path, torch_dtype=torch.bfloat16, _attn_implementation="flash_attention_2" ).to("cuda") ``` #### Simple Inference You preprocess your inputs directly using chat templates and directly passing them ```python messages = [ { "role": "user", "content": [ {"type": "text", "text": "What is in this image?"}, {"type": "image", "path": "path_to_img.png"}, ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device, dtype=torch.bfloat16) generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64) generated_texts = processor.batch_decode( generated_ids, skip_special_tokens=True, ) print(generated_texts[0]) ``` #### Video Inference To use SmolVLM2 for video inference, make sure you have decord installed. ```python messages = [ { "role": "user", "content": [ {"type": "video", "path": "path_to_video.mp4"}, {"type": "text", "text": "Describe this video in detail"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64) generated_texts = processor.batch_decode( generated_ids, skip_special_tokens=True, ) print(generated_texts[0]) ``` #### Multi-image Interleaved Inference You can interleave multiple media with text using chat templates. ```python import torch messages = [ { "role": "user", "content": [ {"type": "text", "text": "What is the similarity between this image "}, {"type": "image", "path": "image_1.png"}, {"type": "text", "text": "and this image "}, {"type": "image", "path": "image_2.png"}, ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) generated_ids = model.generate(**inputs, do_sample=False, max_new_tokens=64) generated_texts = processor.batch_decode( generated_ids, skip_special_tokens=True, ) print(generated_texts[0]) ``` ### Model optimizations ## Misuse and Out-of-scope Use SmolVLM is not intended for high-stakes scenarios or critical decision-making processes that affect an individual's well-being or livelihood. The model may produce content that appears factual but may not be accurate. Misuse includes, but is not limited to: - Prohibited Uses: - Evaluating or scoring individuals (e.g., in employment, education, credit) - Critical automated decision-making - Generating unreliable factual content - Malicious Activities: - Spam generation - Disinformation campaigns - Harassment or abuse - Unauthorized surveillance ### License SmolVLM2 is built upon [SigLIP](https://huggingface.co/google/siglip-base-patch16-512) as image encoder and [SmolLM2](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) for text decoder part. We release the SmolVLM2 checkpoints under the Apache 2.0 license. ## Training Data SmolVLM2 used 3.3M samples for training originally from ten different datasets: [LlaVa Onevision](https://huggingface.co/datasets/lmms-lab/LLaVA-OneVision-Data), [M4-Instruct](https://huggingface.co/datasets/lmms-lab/M4-Instruct-Data), [Mammoth](https://huggingface.co/datasets/MAmmoTH-VL/MAmmoTH-VL-Instruct-12M), [LlaVa Video 178K](https://huggingface.co/datasets/lmms-lab/LLaVA-Video-178K), [FineVideo](https://huggingface.co/datasets/HuggingFaceFV/finevideo), [VideoStar](https://huggingface.co/datasets/orrzohar/Video-STaR), [VRipt](https://huggingface.co/datasets/Mutonix/Vript), [Vista-400K](https://huggingface.co/datasets/TIGER-Lab/VISTA-400K), [MovieChat](https://huggingface.co/datasets/Enxin/MovieChat-1K_train) and [ShareGPT4Video](https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video). In the following plots we give a general overview of the samples across modalities and the source of those samples.
Image description
### Details Image description