Phi-4-multimodal-instruct

22.8K downloads 14 likes on ModelScope updated

ModelScope

LLM-Research/Phi-4-multimodal-instruct · model repository official

Open upstream ↗
Revision
master
Files
31
Downloaded from this source
22.8K

Provider-specific. This path, revision and file list belong to ModelScope 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.

Files 31 · revision master

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.

  • .gitattributes 2.2 KiB 9a14669b38a3
    hashes
    LFS SHA256
    9a14669b38a3c755dc4a347fd077c384bf5237bcbee8a0b6b765d382f1003747
  • added_tokens.json 249 B d4f2aceb0f20
    hashes
    LFS SHA256
    d4f2aceb0f20b71dd1f4bcc7e052e4412946bf281840b8f83d39f259571af486
  • CODE_OF_CONDUCT.md 444 B 9daeae709a0b
    hashes
    LFS SHA256
    9daeae709a0bd71bcfd1c96dc5822ecec5210327eff929da64b0ae7f8faf1444
  • config.json 4.5 KiB 49e1c05f93d4
    hashes
    LFS SHA256
    49e1c05f93d43d7f17715b779a2576235b019f587285d7d914e5b05156253f62
  • configuration.json 73 B f88842172666
    hashes
    LFS SHA256
    f888421726665e8a84b738eed42a64875aed79de8be7daade851ac8bf4c0cef9
  • configuration_phi4mm.py 10.8 KiB bd9609bd47ba
    hashes
    LFS SHA256
    bd9609bd47ba0c87788011e5158a8bd3e1e93165a82a9b764eb7cb048006c949
  • data_summary_card.md 4.4 KiB 7890d72b36e7
    hashes
    LFS SHA256
    7890d72b36e716d2bcad576109b5def2119923aa1915ffffac345b9b7032a7ae
  • generation_config.json 190 B 757daa0d0e89
    hashes
    LFS SHA256
    757daa0d0e89171fe48fc3286341833e95b90bdb7dd3b02a2f8920fb09f85a38
  • LICENSE 1.1 KiB c2cfccb812fe
    hashes
    LFS SHA256
    c2cfccb812fe482101a8f04597dfc5a9991a6b2748266c47ac91b6a5aae15383
  • merges.txt 2.3 MiB 856ce61180bb
    hashes
    LFS SHA256
    856ce61180bb689282eed6b3a6838bb1f438399be23aefe9d20eb379791fb4ad
  • model-00001-of-00003.safetensors LFS 4.7 GiB c46bb03332d8
    hashes
    LFS SHA256
    c46bb03332d82f6a3eaf85bd20af388dd4d4d68b198c2203c965c7381a466094
  • model-00002-of-00003.safetensors LFS 4.6 GiB b3e812c0c8ac
    hashes
    LFS SHA256
    b3e812c0c8acef4e7f5e34d6c9f77a7640ee4a2b93ea351921365ac62f19918d
  • model-00003-of-00003.safetensors LFS 1.1 GiB 7be96b733930
    hashes
    LFS SHA256
    7be96b7339303752634b202d3f377bcf312a03046586eca6cea23347ace1e65a
  • model.safetensors.index.json 234.3 KiB b67dbc7062e1
    hashes
    LFS SHA256
    b67dbc7062e1ccf472faba4222d631dc42929c827fbdaed1ec8e34fe0601819a
  • modeling_phi4mm.py 113.3 KiB e2b44eb7a66d
    hashes
    LFS SHA256
    e2b44eb7a66d6cc54524cee1ff9ba92d0658d435ea8900329ea0dbdb85c6439d
  • phi_4_mm.tech_report.02252025.pdf LFS 5 MiB a5469d9123cb
    hashes
    LFS SHA256
    a5469d9123cbee2b41729db3217cacfeaa96eaf543868caa2eeec7cf2d24547d
  • preprocessor_config.json 482 B 9db19b9663fb
    hashes
    LFS SHA256
    9db19b9663fb86f04c0f11d3a9b7f65a19f13d4543fb4a15bd33f82b0c92d64f
  • processing_phi4mm.py 32 KiB 84914d3e1225
    hashes
    LFS SHA256
    84914d3e12256b4e2186e040c9830c11408468b6774f42afe85e6f8de2626d50
  • processor_config.json 121 B 798fc4cd09c0
    hashes
    LFS SHA256
    798fc4cd09c067053af27f07f0d2b329b471c5b2eb923ceb06efa41dee660c05
  • README.md 63.9 KiB c79dc706ea84
    hashes
    LFS SHA256
    c79dc706ea8478e931981a048164233ae2256b229114e05744610b87f9301293
  • sample_finetune_speech.py 16.3 KiB 0f2d44593bd0
    hashes
    LFS SHA256
    0f2d44593bd0142d3f985473b90d8baf884973fe4d55f139a9a035e333ecc9be
  • sample_finetune_vision.py 19.2 KiB dee385e684dc
    hashes
    LFS SHA256
    dee385e684dcab9c411cef87d41a4fcd897cce528712a23a9c00fd008eb8de3e
  • sample_inference_phi4mm.py 10.3 KiB 22bfc76ecdae
    hashes
    LFS SHA256
    22bfc76ecdaeb2641bc6089a8efcaf2291e017111f0b6db3be91df451adab3a8
  • SECURITY.md 2.6 KiB 7b6976eec43e
    hashes
    LFS SHA256
    7b6976eec43edfa68b79a459dd089c56b7a395916dbf1a01bd11e6d86e12128f
  • special_tokens_map.json 473 B 57491904f868
    hashes
    LFS SHA256
    57491904f8680d4b52ed440f1f7ba48cad1c31ecf3eb453b03484e6ff4723ae8
  • speech_conformer_encoder.py 107.9 KiB 3742827e9457
    hashes
    LFS SHA256
    3742827e945732cc5deea4a95e14004da037044431a94e3f3fac26239e614e3a
  • SUPPORT.md 1.2 KiB 149773411caf
    hashes
    LFS SHA256
    149773411caf2c59cb1a6bfb2c6f070d1d054f1f018e7a80be319a8c384eeaf5
  • tokenizer.json LFS 14.8 MiB 4c1b9f641d4f
    hashes
    LFS SHA256
    4c1b9f641d4f8b7247b8d5007dd3b6a9f6a87cb5123134fe0d326f14d10c0585
  • tokenizer_config.json 3.2 KiB a5da2e45718d
    hashes
    LFS SHA256
    a5da2e45718db78924ad5135a58a80b0303596acf54a1dc5c912c98436ddcaf3
  • vision_siglip_navit.py 76.4 KiB 7d5c053341ee
    hashes
    LFS SHA256
    7d5c053341ee9c099126fe675d5dcdc0ed5c0246f92fffdec78a1ab2f804e28d
  • vocab.json 3.7 MiB 6cb65a857824
    hashes
    LFS SHA256
    6cb65a857824fa6615bb1782d95d882617a8bbce1da0317118586b36f39e98bd