{"_id":"66bfe546a15b4eed7f6609a7","id":"microsoft/Phi-3.5-vision-instruct","private":false,"pipeline_tag":"image-text-to-text","library_name":"transformers","tags":["transformers","safetensors","phi3_v","text-generation","nlp","code","vision","image-text-to-text","conversational","custom_code","multilingual","arxiv:2404.14219","license:mit","region:us"],"downloads":752494,"likes":739,"modelId":"microsoft/Phi-3.5-vision-instruct","author":"microsoft","sha":"12b77fb40b63a2c73c68243d3f767aab688a1b2a","lastModified":"2025-12-10T20:24:07.000Z","gated":false,"disabled":false,"widgetData":[{"messages":[{"role":"user","content":"<|image_1|>Can you describe what you see in the image?"}]}],"model-index":null,"config":{"architectures":["Phi3VForCausalLM"],"auto_map":{"AutoConfig":"configuration_phi3_v.Phi3VConfig","AutoModelForCausalLM":"modeling_phi3_v.Phi3VForCausalLM"},"model_type":"phi3_v","tokenizer_config":{"bos_token":"<s>","chat_template":"{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}","eos_token":"<|endoftext|>","pad_token":"<|endoftext|>","unk_token":"<unk>","use_default_system_prompt":false}},"cardData":{"license":"mit","license_link":"https://huggingface.co/microsoft/Phi-3.5-vision-instruct/resolve/main/LICENSE","language":["multilingual"],"pipeline_tag":"image-text-to-text","tags":["nlp","code","vision"],"inference":{"parameters":{"temperature":0.7}},"widget":[{"messages":[{"role":"user","content":"<|image_1|>Can you describe what you see in the image?"}]}],"library_name":"transformers"},"transformersInfo":{"auto_model":"AutoModelForCausalLM","custom_class":"modeling_phi3_v.Phi3VForCausalLM","pipeline_tag":"text-generation"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"CODE_OF_CONDUCT.md"},{"rfilename":"LICENSE"},{"rfilename":"README.md"},{"rfilename":"SECURITY.md"},{"rfilename":"SUPPORT.md"},{"rfilename":"config.json"},{"rfilename":"configuration_phi3_v.py"},{"rfilename":"data_summary_card.md"},{"rfilename":"generation_config.json"},{"rfilename":"model-00001-of-00002.safetensors"},{"rfilename":"model-00002-of-00002.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"modeling_phi3_v.py"},{"rfilename":"preprocessor_config.json"},{"rfilename":"processing_phi3_v.py"},{"rfilename":"processor_config.json"},{"rfilename":"sample_inference.py"},{"rfilename":"special_tokens_map.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"}],"spaces":["embedl/hfviewer","VIDraft/global-llm-leaderboard","aquanode/gpu-vram-calculator","MaziyarPanahi/Phi-3.5-Vision","TIGER-Lab/MEGA-Bench","KBaba7/Quant","jiuhai/Florence-VL-8B","maxiw/Phi-3.5-vision","FallnAI/Quantize-HF-Models","openfree/LLM_Quantization","bhaskartripathi/LLM_Quantization","Agents-MCP-Hackathon/Art-Historian-AI","ruslanmv/convert_to_gguf","arad1367/Phi-3.5-Chatbot-Vision-App","seawolf2357/LLM_Quantization","mrfakename/TB-OCR","gizemsarsinlar/Phi-3.5-Artwork-Analysis","NotASI/Phi-3.5-Vision-128k","SunderAli17/Image_captioning_Phi_Vision","totolook/Quant","K00B404/LLM_Quantization","sagar007/phi-vision-math-assistant","awacke1/Leaderboard-Deepseek-Gemini-Grok-GPT-Qwen","gizemsarsinlar/Art-Historian-AI","sagar007/Multimodal_App","jiuhai/Florence-VL-3B","dearce/entity-identifier-api","dawit45/Omni-Health-Prime","dawit45/AETHER-HEALTH-PRIME","dawit45/Titan-Health-OS-Sovereign-Command-Edition","Xlnk/Quantize-HF-Models","exploitz3r0bbd/Quantize-HF-Models","Oss11/Quantize-HF-Models","prockot/biomed-paper-extractor","ginipick/Phi-35-vision","Afrinetwork/vs","Afrinetwork/vs1","cuirh/microsoft-Phi-3.5-vision-instruct","venkatvijay/microsoft-Phi-3.5-vision-instruct","wysthinker123/microsoft-Phi-3.5-vision-instruct","jason69/test","ja3noon/microsoft-Phi-3.5-vision-instruct","mohammedhetemy/microsoft-Phi-3.5-vision-instruct","Themoneybuddha/microsoft-Phi-3.5-vision-instruct","nlpravi/microsoft-Phi-3.5-vision-instruct","minimaxa/microsoft-Phi-3.5-vision-instruct","fgjjhih/microsoft-Phi-3.5-vision-instruct","KennethKong/microsoft-Phi-3.5-vision-instruct","Satyam-Singh/LLaVa-Vision","gendev/microsoft-Phi-3.5-vision-instruct","franzese/microsoft-Phi-3.5-vision-instruct","Pxluthor/microsoft-Phi-3.5-vision-instruct","raedEBHAR/microsoft-Phi-3.5-vision-instruct","LeafeLine/microsoft-Phi-3.5-vision-instruct","B1999/imgtotxt","hualianyun/microsoft-Phi-3.5-vision-instruct","harish907/microsoft-Phi-3.5-vision-instruct","CaramelTEQUILA/microsoft-Phi-3.5-vision-instruct","kj1012/microsoft-Phi-3.5-vision-instruct","Aarya-Gupta/microsoft-Phi-3.5-vision-instruct","seawolf2357/wisemath","danirolopes/microsoft-Phi-3.5-vision-instruct","xuanbach2809/microsoft-Phi-3.5-vision-instruct","69cowboy69/microsoft-Phi-3.5-vision-instruct","apanasenko/microsoft-Phi-3.5-vision-instruct","Dunirov/microsoft-Phi-3.5-vision-instruct","sreesaiarjun/microsoft-Phi-3.5-vision-instruct","aa1223/image_bot","Z0RGzzz/microsoft-Phi-3.5-vision-instruct","rajkamerkar/microsoft-Phi-3.5-vision-instruct","YIYUEME/microsoft-Phi-3.5-vision-instruct","Hehe125/microsoft-Phi-3.5-vision-instruct","artemgurskiy/microsoft-Phi-3.5-vision-instruct","Arieff22/microsoft-Phi-3.5-vision-instruct","karankalbhor23/Instagram_caption_generator","5urabhi1/phi3","akshay0000/microsoft-Phi-3.5-vision-instruct","samia-d/VideoSummarizer_using_Multimodel","estebanwasinger/microsoft-Phi-3.5-vision-instruct","estebanwasinger/microsoft-Phi-3.5-vision-instruct2","raringsunny-ai/microsoft-Phi-3.5-vision-instruct","TannedCung/microsoft-Phi-3.5-vision-instruct","mboushaba/Phi-3.5-vision-instruct-on-CPU","snehalsas/Phi-3.5-vision","VIDYASREE24/microsoft-Phi-3.5-vision-instruct","Stafman/microsoft-Phi-3.5-vision-instruct","Abhilash0804/microsoft-Phi-3.5-vision","Abhilash0804/microsoft-Phi-3.5-vision-inst","aci11/TB-OCR","Elyess/microsoft-Phi-3.5-vision-instruct","Abhilash0804/microsoft-Phi-3.5-vision-instruct","LMR3/microsoft-Phi-3.5-vision-instruct","hollywood210/microsoft-Phi-3.5-vision-instruct3","Ayush0804/mathMentor","Utiric/Phi-3.5-Vision","tomasruiz/multimodal-vibe-check","PsamSahil/microsoft-Phi-3.5-vision-instruct","Edwingrow16/microsoft-Phi-3.5-vision-instruct","deNikk/phi-3.5-vision-fastapi","abdullahalioo/vision"],"createdAt":"2024-08-16T23:48:22.000Z","safetensors":{"parameters":{"BF16":4146621440},"total":4146621440},"usedStorage":8293330888}