bertin-base-stepwise-exp-512seqlen download | Hugging Bay

Q: What is this model?

bertin-project/bertin-base-stepwise-exp-512seqlen is an open-weights language model for masked-language modeling published by bertin-project, added to Hugging Bay Sep 25, 2026. Model from Hugging Face for fill mask: bertin-project/bertin-base-stepwise-exp-512seqlen · transformers

Q: Can I use it commercially?

It is released under the cc-by-4.0 license. Commercial use is allowed. cc-by-4.0: commercial use, modification, and redistribution are permitted with attribution.

Q: How big is it?

Hosted here: 5 files, 500.3 MB. Full repo upstream: 6.56 GB. The recommended download, model.safetensors, is 498.8 MB.

Q: What can I download here?

Hosted here: 5 files, 500.3 MB. Full repo upstream: 6.56 GB. The original release is at https://huggingface.co/bertin-project/bertin-base-stepwise-exp-512seqlen.

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-bertin-project-bertin-base-stepwise-exp-512seqlen/safety on Hugging Bay.

Q: Will bertin-project/bertin-base-stepwise-exp-512seqlen 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.

bertin-project

bertin-base-stepwise-exp-512seqlen

bertin-project/bertin-base-stepwise-exp-512seqlen

Model details

masked-language modelingLicense: cc-by-4.0SHA-256 recorded for 39 of 77 filessafetensors · BIN

Content controls: not assessed.

Listed for predicting masked text; for developers working with masked language models. Catalog sources: license, cardMetadata.license, 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-bertin-project-bertin-base-stepwise-exp-512seqlen/model.safetensors",
    "model.safetensors",
)

Other ways

Run it on your computerOpen in Hugging Bay appSend to a computerApp links support one GGUF file.

5 hosted of 77 listed · Hashes recorded. Date not recorded.

Selected downloadmodel.safetensors499 MB · 1 file Download · 499 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 77 listed

Hashes recorded. Date not recorded.

File	Size	SHA-256	Source	Download
Weights
`model.safetensors` Default	498.8 MB	`cbd03348…bd873667` `cbd033487864e6893134c57842481ac75da48c9930f78ef78941c2d9bd873667`	Hosted	Download
`pytorch_model.bin`	498.9 MB	`06c60621…8002d4b9` `06c60621f443054b98aa2dc500b083ddeee3dd86e2824265efb7bd7e8002d4b9`	Upstream only	File metadata
Tokenizer & config
`config.json`	618 bytes	`3fbb0eb8…af6f000e` `3fbb0eb8d123b8543387c7256bf3a4706f138ff340d5e577fe97daacaf6f000e`	Hosted	Download
`configs/base/config.json`	666 bytes	—	Upstream only	File metadata
`configs/base/tokenizer.json`	1.47 MB	—	Upstream only	File metadata
`configs/large/config.json`	619 bytes	—	Upstream only	File metadata
`configs/large/tokenizer.json`	1.47 MB	—	Upstream only	File metadata
`convert.py`	876 bytes	—	Upstream only	File metadata
`flax_model.msgpack`	249.8 MB	`3a80ec61…3a415b92` `3a80ec619ededfbd4e9b69ec8ed53e4716447f0d49f33d7c1dd0c8933a415b92`	Upstream only	File metadata
`merges.txt`	513.8 KB	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-45000/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-45000/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-45000/flax_model.msgpack`	249.8 MB	`2bfec79c…8cf74b98` `2bfec79c06dbe792dd8668ce939a6240945f2f75f7e31b80b5f5c9d28cf74b98`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-45000/optimizer_state.msgpack`	499.5 MB	`2a9133a0…2232f9a2` `2a9133a05008cc9387dd2616518a02c3ab756bed4f17ec29c3cc3d6a2232f9a2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-45000/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-45000/training_state.json`	15 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-46000/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-46000/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-46000/flax_model.msgpack`	249.8 MB	`5c7d4eb9…cfc2366b` `5c7d4eb96066429cc62a1c0eff3317892b2e70dce9d0815d749515d1cfc2366b`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-46000/optimizer_state.msgpack`	499.5 MB	`3aae4f1c…888fa9db` `3aae4f1c6b03e9b709991c3f6b5b0bc30a0eb756ee13c47348de3c88888fa9db`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-46000/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-46000/training_state.json`	15 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-47000/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-47000/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-47000/flax_model.msgpack`	249.8 MB	`cf2e0a84…1adbf1fa` `cf2e0a8447d4d762862755db833dda04a149889cb930f56c336aa8861adbf1fa`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-47000/optimizer_state.msgpack`	499.5 MB	`906a9902…42467117` `906a99024914c38872d8a52f4bfffc9aab9d680e8b6b177c41e86d7742467117`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-47000/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-47000/training_state.json`	15 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-48000/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-48000/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-48000/flax_model.msgpack`	249.8 MB	`24ed996d…65cfe3b5` `24ed996d5623269b9afc7dd278943915670e3406733303a84439a15d65cfe3b5`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-48000/optimizer_state.msgpack`	499.5 MB	`82d6533e…3fb487a6` `82d6533e1795216fc55d7a16252cacb039b1fe419c56257c19f869123fb487a6`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-48000/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-48000/training_state.json`	15 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49000/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49000/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49000/flax_model.msgpack`	249.8 MB	`b9361bf5…f2f99bc2` `b9361bf57ad2ead83a8e61463af52a266432dbe017ac67e69e4fc14ff2f99bc2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49000/optimizer_state.msgpack`	499.5 MB	`0a36b556…4f1acac1` `0a36b556f0aa465dd239707419da9b91e96b3a21d626edcdc79b1d504f1acac1`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49000/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49000/training_state.json`	15 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49999/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49999/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49999/flax_model.msgpack`	249.8 MB	`3a80ec61…3a415b92` `3a80ec619ededfbd4e9b69ec8ed53e4716447f0d49f33d7c1dd0c8933a415b92`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49999/optimizer_state.msgpack`	499.5 MB	`454081a0…5a502328` `454081a0a1386f88384007ec81b6564461b3fea4611907b1ffdcca605a502328`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49999/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/checkpoints/checkpoint-49999/training_state.json`	15 bytes	—	Upstream only	File metadata
`outputs/config.json`	618 bytes	—	Upstream only	File metadata
`outputs/data_collator.joblib`	1.47 MB	`e02a6e9c…47b161ee` `e02a6e9cfa63cb321cac9402efd29841b652999fcbf787800ae050e747b161ee`	Upstream only	File metadata
`outputs/events.out.tfevents.1627258355.tablespoon.3000110.3.v2`	7.36 MB	`67436853…314d2469` `67436853ad44fa6bb220a27f80ae4ac2234c4c97ba1f6f2f187eb535314d2469`	Upstream only	File metadata
`outputs/flax_model.msgpack`	249.8 MB	`3a80ec61…3a415b92` `3a80ec619ededfbd4e9b69ec8ed53e4716447f0d49f33d7c1dd0c8933a415b92`	Upstream only	File metadata
`outputs/optimizer_state.msgpack`	499.5 MB	`454081a0…5a502328` `454081a0a1386f88384007ec81b6564461b3fea4611907b1ffdcca605a502328`	Upstream only	File metadata
`outputs/training_args.joblib`	1.87 KB	`4dcde99c…eebeb7c2` `4dcde99c91fe01c5143995806e1d6595b728cb8ed0a2d9f2f3c5610aeebeb7c2`	Upstream only	File metadata
`outputs/training_state.json`	15 bytes	—	Upstream only	File metadata
`push_to_hub.sh`	84 bytes	—	Upstream only	File metadata
`run_mlm_flax_stream.py`	35.2 KB	—	Upstream only	File metadata
`run_stream.128.sh`	930 bytes	—	Upstream only	File metadata
`run_stream.512.log`	6.34 MB	—	Upstream only	File metadata
`run_stream.512.sh`	968 bytes	—	Upstream only	File metadata
`special_tokens_map.json`	239 bytes	`378eb3bf…22ae554d` `378eb3bf733eb16e65792d7e3fda5b8a4631387ca04d2015199c4d4f22ae554d`	Hosted	Download
`tokenizer.json`	1.47 MB	`90d4fb1e…5cba6c17` `90d4fb1e8230f9f09071ae0e83c327e1937ad33480896c07a79f2ee15cba6c17`	Hosted	Download
`tokenizer_config.json`	292 bytes	`f8ff14df…9a410553` `f8ff14df46341af51a02bcbcf5228f22598aa86b73c8a3551642242b9a410553`	Hosted	Download
`vocab.json`	855.5 KB	—	Upstream only	File metadata
`wandb/debug-internal.log`	52 bytes	—	Upstream only	File metadata
`wandb/debug.log`	43 bytes	—	Upstream only	File metadata
`wandb/latest-run`	28 bytes	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/code/run_mlm_flax_stream.py`	35.2 KB	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/config.yaml`	5.04 KB	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/events.out.tfevents.1627258355.tablespoon.3000110.3.v2`	106 bytes	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/output.log`	55.3 KB	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/requirements.txt`	1.88 KB	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/wandb-metadata.json`	1.59 KB	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/files/wandb-summary.json`	245 bytes	—	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/logs/debug-internal.log`	24.9 MB	`18dd12f7…ddb8f2b2` `18dd12f70c375b860481ce1b76db6aa666ecadc24bafabcd068a857addb8f2b2`	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/logs/debug.log`	5.87 KB	`a2dd7c51…5f8269bd` `a2dd7c5185e79b60bb93ec1d9266f770360846fbb237a1f78837006b5f8269bd`	Upstream only	File metadata
`wandb/run-20210726_001233-17u6inbn/run-17u6inbn.wandb`	12.5 MB	`98150f1b…c4ea0eac` `98150f1bc2fedfdddacff903fa534f92916467f64509d6004410e484c4ea0eac`	Upstream only	File metadata
Docs
`.gitattributes`	936 bytes	—	Upstream only	File metadata
`README.md`	1.48 KB	—	Upstream only	File metadata

Check a download

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.

bertin-base-stepwise-exp-512seqlen

Check a download

Cookies