ms-marco-TinyBERT-L4 safetensors download | Hugging Bay

Q: What is this model?

cross-encoder/ms-marco-TinyBERT-L4 is an open-weights language model for text ranking published by cross-encoder, added to Hugging Bay Jun 30, 2026. Model from Hugging Face for text ranking: cross-encoder/ms-marco-TinyBERT-L4 · sentence transformers

Q: Can I use it commercially?

It is released under the apache-2.0 license. Commercial use is allowed. Permissive open license: commercial use, modification, and redistribution are permitted.

Q: How big is it?

Hosted here: at least 5 listed files; full count and size unknown. Full repo upstream: 562.9 MB. The recommended download, model.safetensors, is 57.4 MB.

Q: What can I download here?

Hosted here: at least 5 listed files; full count and size unknown. Full repo upstream: 562.9 MB. The original release is at https://huggingface.co/cross-encoder/ms-marco-TinyBERT-L4.

Q: File pattern scans

Automated file-pattern scans flagged nothing; not a safety guarantee. 5 hosted files carry a published SHA-256 you can re-hash. The machine-readable verdict is at /api/artifacts/hf-model-cross-encoder-ms-marco-tinybert-l4/safety on Hugging Bay.

Q: Will cross-encoder/ms-marco-TinyBERT-L4 run on my computer?

We can’t check the fit; we don’t know your machine. We don’t have your machine’s specs, so no check ran and no verdict is shown. Answer two quick questions and we’ll estimate, from the memory you tell us, whether it fits your machine. Or skip it; you can still download; fit isn’t checked.

cross-encoder

ms-marco-TinyBERT-L4

cross-encoder/ms-marco-TinyBERT-L4

Model details

text rankingLicense: apache-2.0SHA-256 recorded for 21 of 25 filessafetensors · ONNX · BIN

Content controls: not assessed.

The catalog lists this model for ranking text against a query. Catalog sources: license, cardMetadata.license, tags, task, cardMetadata.pipelineTag.

View as JSON →

Your next step

Use it from code

This Python snippet downloads the selected file. Running the model needs its own library and setup.

from urllib.request import urlretrieve

urlretrieve(
    "https://huggingbay.xyz/api/downloads/hf-model-cross-encoder-ms-marco-tinybert-l4/model.safetensors",
    "model.safetensors",
)

Other ways

This file cannot open in the app. The app supports one GGUF file at a time.

See app requirements

5 hosted of 25 listed · Hashes recorded. Date not recorded.

Selected downloadmodel.safetensors57 MB · 1 file Download · 57 MB (1 file)

Open-file help

Content controls: not assessed.

Check your download →

Compare your file’s SHA-256 with the recorded hash.

5 hosted of 25 listed

Hashes recorded. Date not recorded.

File	Taille	SHA-256	Source	Télécharger
Weights
`model.safetensors` Default	57.4 MB	`c252c9e3…722da835` `c252c9e3b6b9643359d9530048d44e811e7515cc432b192292eb2768722da835`	Hosted	Télécharger
`onnx/model.onnx`	57.5 MB	`12bf3662…5eed0279` `12bf366208f8f62b51d31c1dde6442b62215878ff7e6aec7dad24b365eed0279`	Upstream only	File metadata
`onnx/model_O1.onnx`	57.5 MB	`c82ce80a…25f7fafa` `c82ce80ac1824aad347af9e792ae60955708b83ad081095b36086f8c25f7fafa`	Upstream only	File metadata
`onnx/model_O2.onnx`	57.4 MB	`8ea52278…fab5711b` `8ea522783cea175573e286e6ebe8cf89ac7b0014a6dd532297c7ec76fab5711b`	Upstream only	File metadata
`onnx/model_O3.onnx`	57.4 MB	`51a85a89…c7b7f8b3` `51a85a89a75a8543dfcc7a7f2eca8a929b0877608b37704fc0e820b0c7b7f8b3`	Upstream only	File metadata
`onnx/model_O4.onnx`	28.8 MB	`99f2b42e…06758d09` `99f2b42ebef41788c4b88ad61346ef3cf210f112dca9dec44e49c8ab06758d09`	Upstream only	File metadata
`onnx/model_qint8_arm64.onnx`	14.7 MB	`be6cd308…3d9575cc` `be6cd308a6807e03d6ff90bf3666cb4ee4d55352e61fbfa5f5351e4e3d9575cc`	Upstream only	File metadata
`onnx/model_qint8_avx512.onnx`	14.7 MB	`be6cd308…3d9575cc` `be6cd308a6807e03d6ff90bf3666cb4ee4d55352e61fbfa5f5351e4e3d9575cc`	Upstream only	File metadata
`onnx/model_qint8_avx512_vnni.onnx`	14.7 MB	`be6cd308…3d9575cc` `be6cd308a6807e03d6ff90bf3666cb4ee4d55352e61fbfa5f5351e4e3d9575cc`	Upstream only	File metadata
`onnx/model_quint8_avx2.onnx`	14.7 MB	`40738175…abd72253` `40738175864e381e3b0d0d1f172916456c4067f9cf4dc6e7bb799d84abd72253`	Upstream only	File metadata
`openvino/openvino_model.bin`	57.4 MB	`09c8324c…487d4812` `09c8324cc36f5b5f04d7cc31491aebd46a9241fea6bc3dad8c9ddf55487d4812`	Upstream only	File metadata
`openvino/openvino_model_qint8_quantized.bin`	14.6 MB	`85759cba…e960dcbe` `85759cbab01f9df1bbd135d51138639208815c69a1261b6834c59c11e960dcbe`	Upstream only	File metadata
`pytorch_model.bin`	57.4 MB	`b06785cb…b996dc91` `b06785cbb737ac18adf49a4ac3ce4d724479afc9c133d5e83172b12db996dc91`	Upstream only	File metadata
Tokenizer & config
`CERerankingEvaluator_results.csv`	3.51 KB	`f344ad2b…2bfae81b` `f344ad2becda4e8a1d269fa18c871b3e5365cec983d634b8d5e2f8902bfae81b`	Upstream only	File metadata
`config.json`	612 bytes	`506ea47d…ed92d200` `506ea47d1e2d71a035af9253e5d54418a7033750a62bc011fc81c52aed92d200`	Hosted	Télécharger
`flax_model.msgpack`	57.4 MB	`5de37974…b8b7cfa2` `5de37974f4240be0be8cb67d0bd011c96a84e0af7eefc45129d8e95bb8b7cfa2`	Upstream only	File metadata
`openvino/openvino_model.xml`	147.3 KB	—	Upstream only	File metadata
`openvino/openvino_model_qint8_quantized.xml`	262.7 KB	—	Upstream only	File metadata
`special_tokens_map.json`	132 bytes	`3c3507f3…b2c94dd6` `3c3507f36dff57bce437223db3b3081d1e2b52ec3e56ee55438193ecb2c94dd6`	Hosted	Télécharger
`tokenizer_config.json`	1.33 KB	`a5c2e5a7…25905fd8` `a5c2e5a7b1a29a0702cd28c08a399b5ecc110c263009d17f7e3b415f25905fd8`	Hosted	Télécharger
`train_script.py`	6.59 KB	—	Upstream only	File metadata
`vocab.txt`	231.5 KB	`07eced37…992038a3` `07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3`	Upstream only	File metadata
`tokenizer.json`	711.4 KB	`d241a60d…1f9e5c66` `d241a60d5e8f04cc1b2b3e9ef7a4921b27bf526d9f6050ab90f9267a1f9e5c66`	Hosted	Télécharger
Docs
`.gitattributes`	445 bytes	—	Upstream only	File metadata
`README.md`	3.5 KB	`60df3a72…bf422662` `60df3a727f66f2c4f8529d2bda03261875ae90631caf9872e2246ecbbf422662`	Upstream only	File metadata

Vérifier un téléchargement

In the folder where you saved model.safetensors, run:

macOS

shasum -a 256 -- 'model.safetensors'

Linux

sha256sum -- 'model.safetensors'

Windows

Get-FileHash -LiteralPath 'model.safetensors' -Algorithm SHA256

Compare the result with the recorded SHA-256.

ms-marco-TinyBERT-L4

Vérifier un téléchargement

Cookies