Modelpublic

microsoft/Phi-4-multimodal-instruct

sourceHugging Facemitupdated 10mo agoView on Hugging Face

1.6klikes266kdownloads

dirspeech-lora/

dirvision-lora/

file.gitattributes2 KBdownload

fileadded_tokens.json249 Bdownload

fileCODE_OF_CONDUCT.md444 Bdownload

fileconfig.json5 KBdownload

fileconfiguration_phi4mm.py11 KBdownload

filedata_summary_card.md5 KBdownload

filegeneration_config.json190 Bdownload

fileLICENSE1 KBdownload

filemerges.txt2.3 MBdownload

filemodel-00001-of-00003.safetensors4.65 GBdownload

filemodel-00002-of-00003.safetensors4.61 GBdownload

filemodel-00003-of-00003.safetensors1.12 GBdownload

filemodel.safetensors.index.json234 KBdownload

filemodeling_phi4mm.py113 KBdownload

filephi_4_mm.tech_report.02252025.pdf5.0 MBdownload

filepreprocessor_config.json482 Bdownload

fileprocessing_phi4mm.py32 KBdownload

fileprocessor_config.json121 Bdownload

fileREADME.md64 KBdownload

filesample_finetune_speech.py16 KBdownload

filesample_finetune_vision.py19 KBdownload

filesample_inference_phi4mm.py10 KBdownload

fileSECURITY.md3 KBdownload

filespecial_tokens_map.json473 Bdownload

filespeech_conformer_encoder.py108 KBdownload

fileSUPPORT.md1 KBdownload

filetokenizer_config.json3 KBdownload

filetokenizer.json14.8 MBdownload

filevision_siglip_navit.py76 KBdownload

filevocab.json3.7 MBdownload

microsoft/Phi-4-multimodal-instruct · main · files are served by the source, never re-hosted here