Text Classification
Transformers
Safetensors
English
mimelens
file-type-detection
mime-classification
binary-content
binary-analysis
position-agnostic
libmagic
forensics
packet-inspection
bpe
byte-pair-encoding
custom_code
Eval Results (legacy)
Instructions to use mjbommar/mimelens-001-medium-bpe-4k-s2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mjbommar/mimelens-001-medium-bpe-4k-s2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="mjbommar/mimelens-001-medium-bpe-4k-s2", trust_remote_code=True)# Load model directly from transformers import AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained("mjbommar/mimelens-001-medium-bpe-4k-s2", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "MimeLensForSequenceClassification" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_mimelens.MimeLensConfig", | |
| "AutoModel": "modeling_mimelens.MimeLensModel", | |
| "AutoModelForSequenceClassification": "modeling_mimelens.MimeLensForSequenceClassification" | |
| }, | |
| "model_type": "mimelens", | |
| "torch_dtype": "float32", | |
| "num_labels": 125, | |
| "id2label": { | |
| "0": "application/SIMH-tape-data", | |
| "1": "application/encrypted", | |
| "2": "application/gzip", | |
| "3": "application/javascript", | |
| "4": "application/json", | |
| "5": "application/msword", | |
| "6": "application/mxf", | |
| "7": "application/octet-stream", | |
| "8": "application/pdf", | |
| "9": "application/pgp-keys", | |
| "10": "application/postscript", | |
| "11": "application/vnd.debian.binary-package", | |
| "12": "application/vnd.microsoft.portable-executable", | |
| "13": "application/vnd.ms-excel", | |
| "14": "application/vnd.ms-opentype", | |
| "15": "application/vnd.ms-powerpoint", | |
| "16": "application/vnd.oasis.opendocument.presentation-template", | |
| "17": "application/vnd.oasis.opendocument.spreadsheet", | |
| "18": "application/vnd.oasis.opendocument.spreadsheet-template", | |
| "19": "application/vnd.oasis.opendocument.text-template", | |
| "20": "application/vnd.openxmlformats-officedocument.presentationml.presentation", | |
| "21": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", | |
| "22": "application/vnd.openxmlformats-officedocument.wordprocessingml.document", | |
| "23": "application/vnd.rn-realmedia", | |
| "24": "application/vnd.wordperfect", | |
| "25": "application/wasm", | |
| "26": "application/x-7z-compressed", | |
| "27": "application/x-archive", | |
| "28": "application/x-bzip2", | |
| "29": "application/x-coff", | |
| "30": "application/x-dbf", | |
| "31": "application/x-dosexec", | |
| "32": "application/x-executable", | |
| "33": "application/x-font-pfm", | |
| "34": "application/x-gettext-translation", | |
| "35": "application/x-ms-ne-executable", | |
| "36": "application/x-ndjson", | |
| "37": "application/x-object", | |
| "38": "application/x-ole-storage", | |
| "39": "application/x-pie-executable", | |
| "40": "application/x-rpm", | |
| "41": "application/x-sharedlib", | |
| "42": "application/x-shockwave-flash", | |
| "43": "application/x-stargallery-sdg", | |
| "44": "application/x-stargallery-thm", | |
| "45": "application/x-tar", | |
| "46": "application/x-tex-tfm", | |
| "47": "application/x-wine-extension-ini", | |
| "48": "application/zip", | |
| "49": "application/zlib", | |
| "50": "application/zstd", | |
| "51": "audio/amr", | |
| "52": "audio/flac", | |
| "53": "audio/mpeg", | |
| "54": "audio/ogg", | |
| "55": "audio/x-ape", | |
| "56": "audio/x-hx-aac-adts", | |
| "57": "audio/x-m4a", | |
| "58": "audio/x-wav", | |
| "59": "biosig/atf", | |
| "60": "font/sfnt", | |
| "61": "font/woff", | |
| "62": "font/woff2", | |
| "63": "font/x-postscript-pfb", | |
| "64": "image/bmp", | |
| "65": "image/fits", | |
| "66": "image/gif", | |
| "67": "image/heif", | |
| "68": "image/jpeg", | |
| "69": "image/png", | |
| "70": "image/svg+xml", | |
| "71": "image/tiff", | |
| "72": "image/vnd.adobe.photoshop", | |
| "73": "image/vnd.microsoft.icon", | |
| "74": "image/webp", | |
| "75": "image/x-eps", | |
| "76": "image/x-exr", | |
| "77": "image/x-gimp-gbr", | |
| "78": "image/x-gimp-gih", | |
| "79": "image/x-gimp-pat", | |
| "80": "image/x-jp2-codestream", | |
| "81": "image/x-portable-bitmap", | |
| "82": "image/x-portable-greymap", | |
| "83": "image/x-portable-pixmap", | |
| "84": "image/x-tga", | |
| "85": "image/x-xpixmap", | |
| "86": "inode/symlink", | |
| "87": "inode/x-empty", | |
| "88": "message/rfc822", | |
| "89": "text/csv", | |
| "90": "text/html", | |
| "91": "text/plain", | |
| "92": "text/rtf", | |
| "93": "text/troff", | |
| "94": "text/x-Algol68", | |
| "95": "text/x-asm", | |
| "96": "text/x-c", | |
| "97": "text/x-c++", | |
| "98": "text/x-diff", | |
| "99": "text/x-file", | |
| "100": "text/x-fortran", | |
| "101": "text/x-gimp-ggr", | |
| "102": "text/x-gimp-gpl", | |
| "103": "text/x-java", | |
| "104": "text/x-lisp", | |
| "105": "text/x-m4", | |
| "106": "text/x-makefile", | |
| "107": "text/x-msdos-batch", | |
| "108": "text/x-perl", | |
| "109": "text/x-php", | |
| "110": "text/x-po", | |
| "111": "text/x-ruby", | |
| "112": "text/x-script.python", | |
| "113": "text/x-shellscript", | |
| "114": "text/x-tex", | |
| "115": "text/xml", | |
| "116": "video/3gpp", | |
| "117": "video/mp4", | |
| "118": "video/mpeg", | |
| "119": "video/quicktime", | |
| "120": "video/webm", | |
| "121": "video/x-ivf", | |
| "122": "video/x-matroska", | |
| "123": "video/x-ms-asf", | |
| "124": "video/x-msvideo" | |
| }, | |
| "label2id": { | |
| "application/SIMH-tape-data": 0, | |
| "application/encrypted": 1, | |
| "application/gzip": 2, | |
| "application/javascript": 3, | |
| "application/json": 4, | |
| "application/msword": 5, | |
| "application/mxf": 6, | |
| "application/octet-stream": 7, | |
| "application/pdf": 8, | |
| "application/pgp-keys": 9, | |
| "application/postscript": 10, | |
| "application/vnd.debian.binary-package": 11, | |
| "application/vnd.microsoft.portable-executable": 12, | |
| "application/vnd.ms-excel": 13, | |
| "application/vnd.ms-opentype": 14, | |
| "application/vnd.ms-powerpoint": 15, | |
| "application/vnd.oasis.opendocument.presentation-template": 16, | |
| "application/vnd.oasis.opendocument.spreadsheet": 17, | |
| "application/vnd.oasis.opendocument.spreadsheet-template": 18, | |
| "application/vnd.oasis.opendocument.text-template": 19, | |
| "application/vnd.openxmlformats-officedocument.presentationml.presentation": 20, | |
| "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": 21, | |
| "application/vnd.openxmlformats-officedocument.wordprocessingml.document": 22, | |
| "application/vnd.rn-realmedia": 23, | |
| "application/vnd.wordperfect": 24, | |
| "application/wasm": 25, | |
| "application/x-7z-compressed": 26, | |
| "application/x-archive": 27, | |
| "application/x-bzip2": 28, | |
| "application/x-coff": 29, | |
| "application/x-dbf": 30, | |
| "application/x-dosexec": 31, | |
| "application/x-executable": 32, | |
| "application/x-font-pfm": 33, | |
| "application/x-gettext-translation": 34, | |
| "application/x-ms-ne-executable": 35, | |
| "application/x-ndjson": 36, | |
| "application/x-object": 37, | |
| "application/x-ole-storage": 38, | |
| "application/x-pie-executable": 39, | |
| "application/x-rpm": 40, | |
| "application/x-sharedlib": 41, | |
| "application/x-shockwave-flash": 42, | |
| "application/x-stargallery-sdg": 43, | |
| "application/x-stargallery-thm": 44, | |
| "application/x-tar": 45, | |
| "application/x-tex-tfm": 46, | |
| "application/x-wine-extension-ini": 47, | |
| "application/zip": 48, | |
| "application/zlib": 49, | |
| "application/zstd": 50, | |
| "audio/amr": 51, | |
| "audio/flac": 52, | |
| "audio/mpeg": 53, | |
| "audio/ogg": 54, | |
| "audio/x-ape": 55, | |
| "audio/x-hx-aac-adts": 56, | |
| "audio/x-m4a": 57, | |
| "audio/x-wav": 58, | |
| "biosig/atf": 59, | |
| "font/sfnt": 60, | |
| "font/woff": 61, | |
| "font/woff2": 62, | |
| "font/x-postscript-pfb": 63, | |
| "image/bmp": 64, | |
| "image/fits": 65, | |
| "image/gif": 66, | |
| "image/heif": 67, | |
| "image/jpeg": 68, | |
| "image/png": 69, | |
| "image/svg+xml": 70, | |
| "image/tiff": 71, | |
| "image/vnd.adobe.photoshop": 72, | |
| "image/vnd.microsoft.icon": 73, | |
| "image/webp": 74, | |
| "image/x-eps": 75, | |
| "image/x-exr": 76, | |
| "image/x-gimp-gbr": 77, | |
| "image/x-gimp-gih": 78, | |
| "image/x-gimp-pat": 79, | |
| "image/x-jp2-codestream": 80, | |
| "image/x-portable-bitmap": 81, | |
| "image/x-portable-greymap": 82, | |
| "image/x-portable-pixmap": 83, | |
| "image/x-tga": 84, | |
| "image/x-xpixmap": 85, | |
| "inode/symlink": 86, | |
| "inode/x-empty": 87, | |
| "message/rfc822": 88, | |
| "text/csv": 89, | |
| "text/html": 90, | |
| "text/plain": 91, | |
| "text/rtf": 92, | |
| "text/troff": 93, | |
| "text/x-Algol68": 94, | |
| "text/x-asm": 95, | |
| "text/x-c": 96, | |
| "text/x-c++": 97, | |
| "text/x-diff": 98, | |
| "text/x-file": 99, | |
| "text/x-fortran": 100, | |
| "text/x-gimp-ggr": 101, | |
| "text/x-gimp-gpl": 102, | |
| "text/x-java": 103, | |
| "text/x-lisp": 104, | |
| "text/x-m4": 105, | |
| "text/x-makefile": 106, | |
| "text/x-msdos-batch": 107, | |
| "text/x-perl": 108, | |
| "text/x-php": 109, | |
| "text/x-po": 110, | |
| "text/x-ruby": 111, | |
| "text/x-script.python": 112, | |
| "text/x-shellscript": 113, | |
| "text/x-tex": 114, | |
| "text/xml": 115, | |
| "video/3gpp": 116, | |
| "video/mp4": 117, | |
| "video/mpeg": 118, | |
| "video/quicktime": 119, | |
| "video/webm": 120, | |
| "video/x-ivf": 121, | |
| "video/x-matroska": 122, | |
| "video/x-ms-asf": 123, | |
| "video/x-msvideo": 124 | |
| }, | |
| "problem_type": "single_label_classification", | |
| "vocab_size": 4103, | |
| "hidden_size": 512, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 8, | |
| "head_dim": 64, | |
| "ffn_multiplier_num": 8, | |
| "ffn_multiplier_den": 3, | |
| "max_position_embeddings": 1024, | |
| "rope_theta": 10000.0, | |
| "rms_norm_eps": 1e-06, | |
| "pad_token_id": 2, | |
| "cls_token_id": 4, | |
| "sep_token_id": 5, | |
| "mask_token_id": 6, | |
| "byte_offset": 7, | |
| "cls_pool_dim": 256, | |
| "mimelens_cell_id": "medium/bpe-4k/s2", | |
| "mimelens_vocab_pipeline": "bpe-4k", | |
| "mimelens_tokenizer_hub_id": "mjbommar/binary-tokenizer-001-4k", | |
| "mimelens_pretraining_steps": 22888, | |
| "mimelens_seed": 2 | |
| } |