9daeae709a0bd71bcfd1c96dc5822ecec5210327eff929da64b0ae7f8faf1444 CODE_OF_CONDUCT.md c2cfccb812fe482101a8f04597dfc5a9991a6b2748266c47ac91b6a5aae15383 LICENSE c79dc706ea8478e931981a048164233ae2256b229114e05744610b87f9301293 README.md 7b6976eec43edfa68b79a459dd089c56b7a395916dbf1a01bd11e6d86e12128f SECURITY.md 149773411caf2c59cb1a6bfb2c6f070d1d054f1f018e7a80be319a8c384eeaf5 SUPPORT.md d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486 added_tokens.json 49e1c05f93d43d7f17715b779a2576235b019f587285d7d914e5b05156253f62 config.json bd9609bd47ba0c87788011e5158a8bd3e1e93165a82a9b764eb7cb048006c949 configuration_phi4mm.py 30da70419cb793a917e73c89dc585c802bc8a5cb6c54249ddf138329bff0f2c1 data_summary_card.md 9fcb7788d94740c7925b055a6e66d3bae6e2344ac5caa6ba47da715a3249ef66 examples/what_is_shown_in_this_image.wav 16faff68324cebb79626268af7eb4e2796f6fafd60cfa0ed2bbef927b7d8188a examples/what_is_the_traffic_sign_in_the_image.wav aa123a9f0b51ee8c43136f590f70b639c432375bef28418927bd5117b3b20125 figures/audio_understand.png c23abf6b0335edcb93347c38b9433ec816315ece1815e43735bc9e13f4d28844 figures/multi_image.png 1b325e49c5eba594674ff5e63c093187b10fa55b456ee477fb638dcaab4a58b5 figures/speech_qa.png 37c10d873fac0541541e7c71e30cda0f3809cf2942e71c5ea4f92944b53af145 figures/speech_recog_by_lang.png fe5250ddbe956782eb785250adc346f23fd0728502a381972198a9e77425f187 figures/speech_recognition.png 245a78279a856b2791e92227a7e08fe13af89e9d1ddd88eeaed79f6cf2dd3440 figures/speech_summarization.png 197e800c6bc8ea0ead72cb348b0d86dd28d46d1d888bbd0edb4a1bfb154e8d87 figures/speech_translate.png ccbc37773f73be44b7ac6127bec0be8f0817bf589ee1d0c07d2824c2ce9c61c9 figures/speech_translate_2.png 1a649132fb490a235f3f390ac4f1a5360342d1d130bc6d63d59a30f449f7ecfd figures/vision_radar.png 757daa0d0e89171fe48fc3286341833e95b90bdb7dd3b02a2f8920fb09f85a38 generation_config.json 856ce61180bb689282eed6b3a6838bb1f438399be23aefe9d20eb379791fb4ad merges.txt c46bb03332d82f6a3eaf85bd20af388dd4d4d68b198c2203c965c7381a466094 model-00001-of-00003.safetensors b3e812c0c8acef4e7f5e34d6c9f77a7640ee4a2b93ea351921365ac62f19918d model-00002-of-00003.safetensors 7be96b7339303752634b202d3f377bcf312a03046586eca6cea23347ace1e65a model-00003-of-00003.safetensors b67dbc7062e1ccf472faba4222d631dc42929c827fbdaed1ec8e34fe0601819a model.safetensors.index.json e2b44eb7a66d6cc54524cee1ff9ba92d0658d435ea8900329ea0dbdb85c6439d modeling_phi4mm.py a5469d9123cbee2b41729db3217cacfeaa96eaf543868caa2eeec7cf2d24547d phi_4_mm.tech_report.02252025.pdf 9db19b9663fb86f04c0f11d3a9b7f65a19f13d4543fb4a15bd33f82b0c92d64f preprocessor_config.json 84914d3e12256b4e2186e040c9830c11408468b6774f42afe85e6f8de2626d50 processing_phi4mm.py 798fc4cd09c067053af27f07f0d2b329b471c5b2eb923ceb06efa41dee660c05 processor_config.json 0f2d44593bd0142d3f985473b90d8baf884973fe4d55f139a9a035e333ecc9be sample_finetune_speech.py dee385e684dcab9c411cef87d41a4fcd897cce528712a23a9c00fd008eb8de3e sample_finetune_vision.py 22bfc76ecdaeb2641bc6089a8efcaf2291e017111f0b6db3be91df451adab3a8 sample_inference_phi4mm.py 57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8 special_tokens_map.json ed252a6ae210888ee69f5720bd7e8d8261f0abfda90b18ea6452316c71336df8 speech-lora/adapter_config.json 1c2237461a4d1f9292cd128147bd3f0f70326a48d5d79c8e0f7583b26c095b30 speech-lora/adapter_model.safetensors d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486 speech-lora/added_tokens.json 57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8 speech-lora/special_tokens_map.json 382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea speech-lora/tokenizer.json d51bf28bbdc9915926a0b1908f95cec05f3d10b71af0d27f85344d9a486b03ae speech-lora/tokenizer_config.json 6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd speech-lora/vocab.json 3742827e945732cc5deea4a95e14004da037044431a94e3f3fac26239e614e3a speech_conformer_encoder.py 4c1b9f641d4f8b7247b8d5007dd3b6a9f6a87cb5123134fe0d326f14d10c0585 tokenizer.json a5da2e45718db78924ad5135a58a80b0303596acf54a1dc5c912c98436ddcaf3 tokenizer_config.json efbff3b978dd25e0c3abd7e71a1e9acb9a4f25e13f7430ce035654c0cb159484 vision-lora/adapter_config.json 1620b16722edf701038bf66e3cd46412c7cc5458e58df89e9f92cedb71fcbde8 vision-lora/adapter_model.safetensors d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486 vision-lora/added_tokens.json 57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8 vision-lora/special_tokens_map.json 382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea vision-lora/tokenizer.json d51bf28bbdc9915926a0b1908f95cec05f3d10b71af0d27f85344d9a486b03ae vision-lora/tokenizer_config.json 6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd vision-lora/vocab.json 7d5c053341ee9c099126fe675d5dcdc0ed5c0246f92fffdec78a1ab2f804e28d vision_siglip_navit.py 6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd vocab.json