{"_id":"6a6473d51258ef1584f57b2b","id":"microsoft/Mage-VL","private":false,"pipeline_tag":"image-text-to-text","library_name":"transformers","tags":["transformers","safetensors","mage_vl","image-text-to-text","multimodal","vision-language-model","mage-vl","video-understanding","streaming","conversational","custom_code","arxiv:2607.24904","license:apache-2.0","region:us"],"downloads":44301,"likes":394,"modelId":"microsoft/Mage-VL","author":"microsoft","sha":"d88b153285f1633a61b2f693c59c8576693af185","lastModified":"2026-08-10T09:23:16.000Z","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":{"auto_map":{"AutoConfig":"configuration_mage_vl.MageVLConfig","AutoModel":"modeling_mage_vl.MageVLModel","AutoModelForImageTextToText":"modeling_mage_vl.MageVLForConditionalGeneration","AutoProcessor":"processing_mage_vl.MageVLProcessor","AutoVideoProcessor":"video_processing_mage_vl.MageVLVideoProcessor","AutoModelForCausalLM":"modeling_mage_vl.MageVLForConditionalGeneration"},"model_type":"mage_vl","architectures":["MageVLForConditionalGeneration"],"tokenizer_config":{"bos_token":null,"eos_token":"<|im_end|>","pad_token":"<|endoftext|>","unk_token":null},"chat_template_jinja":"{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"},"cardData":{"license":"apache-2.0","library_name":"transformers","pipeline_tag":"image-text-to-text","tags":["multimodal","vision-language-model","mage-vl","video-understanding","streaming"]},"transformersInfo":{"auto_model":"AutoModelForImageTextToText","custom_class":"modeling_mage_vl.MageVLForConditionalGeneration","pipeline_tag":"image-text-to-text"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"added_tokens.json"},{"rfilename":"assets/mage-vl-cover.png"},{"rfilename":"assets/mage-vl-framework.png"},{"rfilename":"chat_template.jinja"},{"rfilename":"codec_video_processing_mage_vl.py"},{"rfilename":"config.json"},{"rfilename":"configuration_mage_vl.py"},{"rfilename":"examples/dog.jpg"},{"rfilename":"examples/soccer-broadcast.mp4"},{"rfilename":"generation_config.json"},{"rfilename":"inference.py"},{"rfilename":"merges.txt"},{"rfilename":"model-00001-of-00002.safetensors"},{"rfilename":"model-00002-of-00002.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"modeling_mage_vl.py"},{"rfilename":"neural_codec/DCVC/LICENSE.txt"},{"rfilename":"neural_codec/DCVC/NOTICE.txt"},{"rfilename":"neural_codec/DCVC/src/cpp/py_rans/py_rans.cpp"},{"rfilename":"neural_codec/DCVC/src/cpp/py_rans/py_rans.h"},{"rfilename":"neural_codec/DCVC/src/cpp/py_rans/rans.cpp"},{"rfilename":"neural_codec/DCVC/src/cpp/py_rans/rans.h"},{"rfilename":"neural_codec/DCVC/src/cpp/py_rans/rans_byte.h"},{"rfilename":"neural_codec/DCVC/src/cpp/setup.py"},{"rfilename":"neural_codec/DCVC/src/layers/cuda_inference.py"},{"rfilename":"neural_codec/DCVC/src/layers/extensions/inference/bind.cpp"},{"rfilename":"neural_codec/DCVC/src/layers/extensions/inference/common.h"},{"rfilename":"neural_codec/DCVC/src/layers/extensions/inference/def.h"},{"rfilename":"neural_codec/DCVC/src/layers/extensions/inference/impl.cpp"},{"rfilename":"neural_codec/DCVC/src/layers/extensions/inference/kernel.cu"},{"rfilename":"neural_codec/DCVC/src/layers/extensions/inference/setup.py"},{"rfilename":"neural_codec/DCVC/src/layers/layers.py"},{"rfilename":"neural_codec/DCVC/src/models/common_model.py"},{"rfilename":"neural_codec/DCVC/src/models/entropy_models.py"},{"rfilename":"neural_codec/DCVC/src/models/image_model.py"},{"rfilename":"neural_codec/DCVC/src/models/video_model.py"},{"rfilename":"neural_codec/DCVC/src/utils/common.py"},{"rfilename":"neural_codec/DCVC/src/utils/metrics.py"},{"rfilename":"neural_codec/DCVC/src/utils/stream_helper.py"},{"rfilename":"neural_codec/DCVC/src/utils/transforms.py"},{"rfilename":"neural_codec/DCVC/src/utils/video_reader.py"},{"rfilename":"neural_codec/DCVC/src/utils/video_writer.py"},{"rfilename":"neural_codec/README.md"},{"rfilename":"neural_codec/canvas_assembler.py"},{"rfilename":"neural_codec/codec_dcvc_config.py"},{"rfilename":"neural_codec/codec_loader.py"},{"rfilename":"neural_codec/codec_tools/__init__.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/__init__.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/energy_sampling.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/frame_utils.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/patch_utils.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/scoring.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/utils.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/video_probe.py"},{"rfilename":"neural_codec/codec_tools/codec_patch_gop/video_processor.py"},{"rfilename":"neural_codec/codec_tools/pipeline/__init__.py"},{"rfilename":"neural_codec/codec_tools/pipeline/generate_codec_patch_smart_resize.py"},{"rfilename":"neural_codec/codec_tools/pipeline/process_video_bitcost_mv_mask_collage.py"},{"rfilename":"neural_codec/codec_tools/pipeline/process_video_bitcost_readiness.py"},{"rfilename":"neural_codec/dcvc_readiness_gen.py"},{"rfilename":"neural_codec/dcvc_rt_engine.py"},{"rfilename":"neural_codec/dcvc_rt_inter.tar"},{"rfilename":"neural_codec/dcvc_rt_intra.tar"},{"rfilename":"neural_codec/infer_dcvc_rt.py"},{"rfilename":"neural_codec/precompute_dcvc_rt.py"},{"rfilename":"neural_codec/reproduce_bench.py"},{"rfilename":"preprocessor_config.json"},{"rfilename":"processing_mage_vl.py"},{"rfilename":"special_tokens_map.json"},{"rfilename":"streammind_gate.py"},{"rfilename":"streammind_gate.safetensors"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"video_preprocessor_config.json"},{"rfilename":"video_processing_mage_vl.py"},{"rfilename":"vocab.json"}],"spaces":["microsoft/mage-vl-demo","bcoster/mage-vl-demo","SeedOfEvil/ReplayForge","lienthealien/mage-vl-demo","lienthealien/lora-ease"],"createdAt":"2026-07-25T08:29:09.000Z","safetensors":{"parameters":{"BF16":4741793792},"total":4741793792},"usedStorage":10842931443}