Hugging Peers

Phi-4-multimodal-instruct

☆ Save
by microsoft automatic-speech-recognition transformers mit
108.4K downloads 1.6K likes on Hugging Face updated

Hugging Face

microsoft/Phi-4-multimodal-instruct · model repository official

Open upstream ↗
Revision
93f923e1a772
Files
55
Downloaded from this source
108.4K

Provider-specific. This path, revision and file list belong to Hugging Face alone. A different source for the same model may publish different files, or the same names with different contents — which is why nothing here is merged across providers.

Tensor information · safetensors

Parameters
5.6B
Precision · BF16
5.6B params

Parameter counts and precision come from the provider's safetensors metadata. Per-tensor shapes live in the file header and are not part of our index.

Files 55 · revision 93f923e1a772

Hashes: Git OID identifies the file in the repository; LFS SHA256 is the fingerprint of a large file's contents; Xet is the provider's own content fingerprint. Expand “hashes” on any row for the full values.

  • examples/
  • figures/
  • speech-lora/
    • adapter_config.json 465 B
      hashes
      Git OID
      3fb5a8d7d3f8e87564a4f6d1d9c78a5dd7eb27da
    • adapter_model.safetensors LFS 880 MiB 1c2237461a4d
      hashes
      Git OID
      9726355d36b4b921e7d413583e1c376c8247e714
      LFS SHA256
      1c2237461a4d1f9292cd128147bd3f0f70326a48d5d79c8e0f7583b26c095b30
      Xet hash
      afd26c6ef6880e52852e65911fe16d3cdc503e95a334a5e5c3016fbf64938941
      Pointer size
      134 B
    • added_tokens.json 249 B
      hashes
      Git OID
      af52cde61cc39aca58f7b7f04116b317116e75dd
    • special_tokens_map.json 473 B
      hashes
      Git OID
      330140f0678dc92ae683e1c1cccffc6a001251ae
    • tokenizer.json LFS 14.8 MiB 382cc235b56c
      hashes
      Git OID
      3a12dacd8e86802d0229d810d3cc69ab548adf0a
      LFS SHA256
      382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
      Xet hash
      0e0643acc564bb0bb41e1fc82b35b0bd1824a89e58d3969295aa23a3d1d373d5
      Pointer size
      133 B
    • tokenizer_config.json 3.2 KiB
      hashes
      Git OID
      5212793489cd86ed0ed0517e178ebccb0c8bee7f
    • vocab.json 3.7 MiB
      hashes
      Git OID
      ea953a43348cdb3776cb7fd9ea02e3784febde34
  • vision-lora/
    • adapter_config.json 464 B
      hashes
      Git OID
      72c07d66d7ac6ad95620f249fd381c820ee8b79c
    • adapter_model.safetensors LFS 704 MiB 1620b16722ed
      hashes
      Git OID
      8b980e724fef4b12668899fbf52be64ce0989faa
      LFS SHA256
      1620b16722edf701038bf66e3cd46412c7cc5458e58df89e9f92cedb71fcbde8
      Xet hash
      734f733651b1be9cde9c0f12edf53d03c41bd7b13a30fbd0af4f43be5bcf0b0e
      Pointer size
      134 B
    • added_tokens.json 249 B
      hashes
      Git OID
      af52cde61cc39aca58f7b7f04116b317116e75dd
    • special_tokens_map.json 473 B
      hashes
      Git OID
      330140f0678dc92ae683e1c1cccffc6a001251ae
    • tokenizer.json LFS 14.8 MiB 382cc235b56c
      hashes
      Git OID
      3a12dacd8e86802d0229d810d3cc69ab548adf0a
      LFS SHA256
      382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
      Xet hash
      0e0643acc564bb0bb41e1fc82b35b0bd1824a89e58d3969295aa23a3d1d373d5
      Pointer size
      133 B
    • tokenizer_config.json 3.2 KiB
      hashes
      Git OID
      5212793489cd86ed0ed0517e178ebccb0c8bee7f
    • vocab.json 3.7 MiB
      hashes
      Git OID
      ea953a43348cdb3776cb7fd9ea02e3784febde34
  • .gitattributes 1.6 KiB
    hashes
    Git OID
    b4d92b0fce26e0ebb62e1a329909e4bfacf82552
  • added_tokens.json 249 B
    hashes
    Git OID
    af52cde61cc39aca58f7b7f04116b317116e75dd
  • CODE_OF_CONDUCT.md 444 B
    hashes
    Git OID
    f9ba8cf65f3e3104dd061c178066ec8247811f33
  • config.json 4.5 KiB
    hashes
    Git OID
    6f294fb015412e07443c36ecc01233c1211f8d0d
  • configuration_phi4mm.py 10.8 KiB
    hashes
    Git OID
    0abf4196bcf52128567ad4008062fcb2c0c45e33
  • data_summary_card.md 4.5 KiB
    hashes
    Git OID
    8b691d0fc283dfd39dc4161d5551d59d469ac10a
  • generation_config.json 190 B
    hashes
    Git OID
    98769448b636893c5e5780bd4beb070e95a70b48
  • LICENSE 1.1 KiB
    hashes
    Git OID
    9e841e7a26e4eb057b24511e7b92d42b257a80e5
  • merges.txt 2.3 MiB
    hashes
    Git OID
    dcecc4524288b351bbd0da8028e74e9b5bcdb9b5
  • model-00001-of-00003.safetensors LFS 4.7 GiB c46bb03332d8
    hashes
    Git OID
    8f1534da1d87e55619f4feb38887a867084aa47d
    LFS SHA256
    c46bb03332d82f6a3eaf85bd20af388dd4d4d68b198c2203c965c7381a466094
    Xet hash
    4d1cd7cc791221749a2eb3508ec64e93218e0e1b6b88f704bac25b59cd175a7a
    Pointer size
    135 B
  • model-00002-of-00003.safetensors LFS 4.6 GiB b3e812c0c8ac
    hashes
    Git OID
    854d60c0126d32d9afe42b56bd5efeb7e13e198a
    LFS SHA256
    b3e812c0c8acef4e7f5e34d6c9f77a7640ee4a2b93ea351921365ac62f19918d
    Xet hash
    cd52801025256e261ff6813f5a55f5d1c4afba0d90e1ccf62163db057a87c9fd
    Pointer size
    135 B
  • model-00003-of-00003.safetensors LFS 1.1 GiB 7be96b733930
    hashes
    Git OID
    b33626fda237e620032bfe2de54d90f4cacdc36d
    LFS SHA256
    7be96b7339303752634b202d3f377bcf312a03046586eca6cea23347ace1e65a
    Xet hash
    b1e330fdf01d733883117e86cba580457cb7a93d220c3a150e19b6492226da33
    Pointer size
    135 B
  • model.safetensors.index.json 234.3 KiB
    hashes
    Git OID
    dde52c7dc181beab5d91b97ba009ef4fc6626594
  • modeling_phi4mm.py 113.3 KiB
    hashes
    Git OID
    31fe013b98d269c5962e17968bc376992704036f
  • phi_4_mm.tech_report.02252025.pdf LFS 5 MiB a5469d9123cb
    hashes
    Git OID
    1b22e6e264e7fd1f56ecbfbd86de0bd559579924
    LFS SHA256
    a5469d9123cbee2b41729db3217cacfeaa96eaf543868caa2eeec7cf2d24547d
    Xet hash
    4985fd88844350c8eabce2ba82a9777d24a77c795a358b818b83aab9b301194b
    Pointer size
    132 B
  • preprocessor_config.json 482 B
    hashes
    Git OID
    6dd46225a7f8996f811adb74f920995ef206260a
  • processing_phi4mm.py 32 KiB
    hashes
    Git OID
    c4536317e3bef10a53438522682c7539663daad0
  • processor_config.json 121 B
    hashes
    Git OID
    e30d7f7420bde05b724784200abc9c4df4731edf
  • README.md 63.9 KiB
    hashes
    Git OID
    638090d959b0338919920f58c6cca1ab5dd9db7b
  • sample_finetune_speech.py 16.3 KiB
    hashes
    Git OID
    485e84b714e42ca6a62d0c00b643a42fd045b1af
  • sample_finetune_vision.py 19.2 KiB
    hashes
    Git OID
    0b669758018d8c780058cfaa8fb40a6518bbcd91
  • sample_inference_phi4mm.py 10.3 KiB
    hashes
    Git OID
    9e425b0d04dbc3c6fc616f4acdabe610ab6b893b
  • SECURITY.md 2.6 KiB
    hashes
    Git OID
    b3c89efc852e22f71eabf5dfbc6ac62493425eb6
  • special_tokens_map.json 473 B
    hashes
    Git OID
    330140f0678dc92ae683e1c1cccffc6a001251ae
  • speech_conformer_encoder.py 107.9 KiB
    hashes
    Git OID
    d1b0dd2aa513530fa927b5409b69f15364b243b9
  • SUPPORT.md 1.2 KiB
    hashes
    Git OID
    291d4d43733f4c15a81ff598ec1c99fd6c18f64c
  • tokenizer.json LFS 14.8 MiB 4c1b9f641d4f
    hashes
    Git OID
    feafd52abfa48efec92864efd8bb884f9ac53353
    LFS SHA256
    4c1b9f641d4f8b7247b8d5007dd3b6a9f6a87cb5123134fe0d326f14d10c0585
    Xet hash
    8b4a9b9b2df5883c5cfd7a675bd3c80f971a5dc6ad1d08252f000d3c05457b6e
    Pointer size
    133 B
  • tokenizer_config.json 3.2 KiB
    hashes
    Git OID
    eb04aec9ccf2d3bc9f8d28bc8d4e2d4c3a144460
  • vision_siglip_navit.py 76.4 KiB
    hashes
    Git OID
    e3da680471f4432a9828b42c7ad8de0e72e08e66
  • vocab.json 3.7 MiB
    hashes
    Git OID
    ea953a43348cdb3776cb7fd9ea02e3784febde34