{"_id":"67aaf6fe385da1f07cd40b05","id":"HuggingFaceTB/SmolVLM2-500M-Video-Instruct","private":false,"pipeline_tag":"image-text-to-text","library_name":"transformers","tags":["transformers","onnx","safetensors","smolvlm","image-text-to-text","conversational","en","dataset:HuggingFaceM4/the_cauldron","dataset:HuggingFaceM4/Docmatix","dataset:lmms-lab/LLaVA-OneVision-Data","dataset:lmms-lab/M4-Instruct-Data","dataset:HuggingFaceFV/finevideo","dataset:MAmmoTH-VL/MAmmoTH-VL-Instruct-12M","dataset:lmms-lab/LLaVA-Video-178K","dataset:orrzohar/Video-STaR","dataset:Mutonix/Vript","dataset:TIGER-Lab/VISTA-400K","dataset:Enxin/MovieChat-1K_train","dataset:ShareGPT4Video/ShareGPT4Video","arxiv:2504.05299","base_model:HuggingFaceTB/SmolVLM-500M-Instruct","base_model:quantized:HuggingFaceTB/SmolVLM-500M-Instruct","license:apache-2.0","endpoints_compatible","region:us"],"downloads":1411432,"likes":174,"modelId":"HuggingFaceTB/SmolVLM2-500M-Video-Instruct","author":"HuggingFaceTB","sha":"7b375e1b73b11138ff12fe22c8f2822d8fe03467","lastModified":"2025-04-08T07:25:40.000Z","gated":false,"disabled":false,"widgetData":[{"text":"Hi, what can you help me with?"},{"text":"What is 84 * 3 / 2?"},{"text":"Tell me an interesting fact about the universe!"},{"text":"Explain quantum computing in simple terms."}],"model-index":null,"config":{"architectures":["SmolVLMForConditionalGeneration"],"model_type":"smolvlm","processor_config":{"chat_template":"<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"},"tokenizer_config":{"bos_token":"<|im_start|>","chat_template":"<|im_start|>{% for message in messages %}{{message['role'] | capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>\n{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}","eos_token":"<end_of_utterance>","pad_token":"<|im_end|>","unk_token":"<|endoftext|>"}},"cardData":{"library_name":"transformers","license":"apache-2.0","datasets":["HuggingFaceM4/the_cauldron","HuggingFaceM4/Docmatix","lmms-lab/LLaVA-OneVision-Data","lmms-lab/M4-Instruct-Data","HuggingFaceFV/finevideo","MAmmoTH-VL/MAmmoTH-VL-Instruct-12M","lmms-lab/LLaVA-Video-178K","orrzohar/Video-STaR","Mutonix/Vript","TIGER-Lab/VISTA-400K","Enxin/MovieChat-1K_train","ShareGPT4Video/ShareGPT4Video"],"pipeline_tag":"image-text-to-text","language":["en"],"base_model":["HuggingFaceTB/SmolVLM-500M-Instruct"]},"transformersInfo":{"auto_model":"AutoModelForMultimodalLM","pipeline_tag":"image-text-to-text","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"added_tokens.json"},{"rfilename":"chat_template.json"},{"rfilename":"config.json"},{"rfilename":"generation_config.json"},{"rfilename":"merges.txt"},{"rfilename":"model.safetensors"},{"rfilename":"onnx/decoder_model_merged.onnx"},{"rfilename":"onnx/decoder_model_merged_bnb4.onnx"},{"rfilename":"onnx/decoder_model_merged_fp16.onnx"},{"rfilename":"onnx/decoder_model_merged_int8.onnx"},{"rfilename":"onnx/decoder_model_merged_q4.onnx"},{"rfilename":"onnx/decoder_model_merged_q4f16.onnx"},{"rfilename":"onnx/decoder_model_merged_quantized.onnx"},{"rfilename":"onnx/decoder_model_merged_uint8.onnx"},{"rfilename":"onnx/embed_tokens.onnx"},{"rfilename":"onnx/embed_tokens_bnb4.onnx"},{"rfilename":"onnx/embed_tokens_fp16.onnx"},{"rfilename":"onnx/embed_tokens_int8.onnx"},{"rfilename":"onnx/embed_tokens_q4.onnx"},{"rfilename":"onnx/embed_tokens_q4f16.onnx"},{"rfilename":"onnx/embed_tokens_quantized.onnx"},{"rfilename":"onnx/embed_tokens_uint8.onnx"},{"rfilename":"onnx/vision_encoder.onnx"},{"rfilename":"onnx/vision_encoder_bnb4.onnx"},{"rfilename":"onnx/vision_encoder_fp16.onnx"},{"rfilename":"onnx/vision_encoder_int8.onnx"},{"rfilename":"onnx/vision_encoder_q4.onnx"},{"rfilename":"onnx/vision_encoder_q4f16.onnx"},{"rfilename":"onnx/vision_encoder_quantized.onnx"},{"rfilename":"onnx/vision_encoder_uint8.onnx"},{"rfilename":"preprocessor_config.json"},{"rfilename":"processor_config.json"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"vocab.json"}],"spaces":["linoyts/LTX-2-3-sync","sergiopaniego/vqa_autonomous_driving_smolvlm2","mrdbourke/FoodExtract-Vision-v1","ArtShumov/Whyx-PROmpTea","AnasKAN/Moraqeb","Zurya/Jarvise","CreatorJarvis/FoodExtract-Vision","smartdigitalnetworks/generativevideo","X-HighVoltage-X/LTX-2.3-Sync","Samarth991/CV-Agent","becteur92/smollvm","blasisd/GAIA_benchmarked_Agent","xco2/smolvlm2-500M-illustration-description","SkyNait/SmolVLM2-on-transformers","NeuralFalcon/Image-to-Prompt","anhkhoiphan/Kumiko_v2.0","jlamperez/mortis","ajayvikram/FoodExtract-Vision-v1","smartdigitalnetworks/ltx-2-TURBO","ninjals/FoodExtract-Vision-v1","berkeruveyik/FoodExtract-Vision","hamidown/unit_8_final","Unnatrathi/caloraify","yanshania/LTX-2-3-sync","Noname24545/LTX-2-3-sync","prakhar-adaf/LTX-2-3-sync","Jaggieasr/LTX-2-3-sync","honesdev/invoice-extractor","Trkaga/LTX-2-3-sync","helmies/LTX-2-3-sync","naicoi/LTX-2-3-sync","FINAL-Bench/LTX-2-3-sync","rahul7star/LTX-2-3","iramadwivedi/LTX-2-3-sync","Maximoose666/LTX-2-3-sync","Rahulgghhbrtt/LTX-2-3-sync","Rahul124566/LTX-2-3-sync","Muralix/LTX-2-3-sync","Ify-2410/LTX-2-3-sync","fffiloni/LTX-2-3-sync","pantelism/FoodExtract-Vision-v1","smartgrowthgear/LTX-Motion","Markdawg/LTX-2-3-sync","pepijn223/robomme-eval-docker","nomanpro/LTX-2-3-sync","Usagert12/LTX-2-3-sync","raubatz/LTX-2-3-sync","huydzhihi/Caloraify","kapilr/LTX-2-3-sync","chanifrusydi/FoodExtract-Vision-v1","2026hbk/FoodExtract-Vision-v1","jhkim3217/FoodExtract-Vision-v1","raubatz/ltx-2-TURBO-outp","venayc/elrobot-training","raubatz/LTX-2-3-sync-copy","raubatz/ltx-2-TURBO-motioncontrol","leilaloren1/fresh","udit74j/FoodExtract-Vision-v1","Jejend/LTX-2-3-sync","Kamaljeyaram07/test","samnoul/Padeliq","Richharvey1978/LTX-2-3-sync","raubatz/ltxturbo-i2v-v2v","evanjaber/calorify-by-img"],"createdAt":"2025-02-11T07:06:38.000Z","safetensors":{"parameters":{"F32":507482304},"total":507482304},"usedStorage":10125731115}