{"success":true,"data":{"author":"Roman Bushuiev, Tomas Pluskal et al. (Pluskal lab)","bucketAccessType":"public","bucketName":"models/roman-bushuiev/DreaMS","bucketPrefix":"","category":"Proteomics","cloudProvider":"huggingface","createdAt":"2026-11-16T15:25:49.268Z","description":"Pre-trained weights for DreaMS (Deep Representations Empowering the Annotation of Mass Spectra), the transformer from the Pluskal lab (Bushuiev et al., Nature Biotechnology 2025) trained self-supervised on GeMS, a large collection of unannotated tandem mass spectra mined from the MassIVE GNPS repository, to embed MS/MS spectra for molecular networking, spectral similarity and property prediction. The mounted repo holds ssl_model.ckpt (the self-supervised model), embedding_model.ckpt and embedding_model_massspecgym.ckpt (fine-tuned embedding models, about 1.2 GB each) and a TorchScript export for non-Python use. Load the checkpoints with the dreams package from the mount path and pair them with the GNPS libraries or Enveda-180 archives. MIT licence.","displayTitle":"DreaMS mass spectrometry foundation model weights","huggingFaceUrl":"https://huggingface.co/roman-bushuiev/DreaMS","id":"8f5d79c9-3ff7-5167-8914-2b38fd28753f","license":"MIT","licenseEvidenceUrl":"https://github.com/pluskal-lab/DreaMS/blob/main/LICENSE","objectCountEstimate":8,"probeStatus":"ok","referenceUrl":"https://www.nature.com/articles/s41587-025-02663-3","region":"us","schemaCard":{"accessHints":[{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"roman-bushuiev/DreaMS\")  # or read /mnt/archive directly"}],"caveats":["HuggingFace metadata: author=roman-bushuiev, license:mit, downloads=0","Weights are read lazily from the mount. Copying them to local disk first is faster when a model is loaded many times."],"format":"binary","generatedAt":"2026-11-17T19:17:26.702Z","layout":{"example":"DreaMS_embedding_model_torchscript.pt","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleObjects":["DreaMS_embedding_model_torchscript.pt","embedding_model.ckpt","embedding_model_massspecgym.ckpt"],"sidecars":[{"bytes":"---\nlicense: mit\n---\n\nPre-trained weights for https://github.com/pluskal-lab/DreaMS.\n\n`DreaMS_embedding_model_torchscript.pt` contains a compiled DreaMS model which can be loaded in non-python environments (e.g., in Java applications via [DJL](https://djl.ai/)).","encoding":"utf8","key":"README.md","name":"README.md","size":262,"truncated":false}],"sourceObjectKey":"DreaMS_embedding_model_torchscript.pt","starterCell":"import os, json\nbase = \"/mnt/archive\"   # this model repo, mounted read-only\nfiles = sorted(os.listdir(base)); print(files)\nprint(\"DreaMS_embedding_model_torchscript.pt\", os.path.getsize(os.path.join(base, \"DreaMS_embedding_model_torchscript.pt\")) // 2**20, \"MB\")","totalObjects":8},"summary":"Pre-trained weights for DreaMS (Deep Representations Empowering the Annotation of Mass Spectra), the transformer from the Pluskal lab (Bushuiev et al., Nature Biotechnology 2025)…","title":"DreaMS mass spectrometry foundation model weights","updatedAt":"2026-11-17T19:17:26.892Z","visibility":"public","websiteUrl":"https://github.com/pluskal-lab/DreaMS"}}