nomic-ai/nomic-embed-text-v1-unsupervised

🤗 Hugging Face sourcesentence-similarityapache-2.01.8 GBother✓ HF checksums availableupdated today

nomic-embed-text-v1-unsupervised: A Reproducible Long Context (8192) Text Embedder

nomic-embed-text-v1-unsupervised is 8192 context length text encoder. This is a checkpoint after contrastive pretraining from multi-stage contrastive training of the final model. The purpose of releasing this checkpoint is to open-source training artifacts from our Nomic Embed Text tech report here

If you want to use a model to extract embeddings, we suggest using nomic-embed-text-v1.

Join the Nomic Community

@nomic-ai is unclaimedAre you nomic-ai on Hugging Face? Claim it now to lock the badge. If someone grabs it first you can still take it back - signing in with the matching Hugging Face account reclaims any unverified handle.

Claim @nomic-ai →

Help seed this model

Have the files? Submit a torrent for review.

Submit a torrent →

Availability & integrityRecorded evidence, not a live download test

Metadata indexed

Original sourceHugging Face metadata retrieved; file downloads not tested heremetadata

Checksum recordOfficial hashes found, awaiting public witnessqueued

TorrentMetadata indexed. Torrent registration is separate from a successful download test.waiting

Peer availabilityReported counts do not prove a complete download. See community torrent test evidence when available.not tested

Source revision: b53d557b15ae63852847c222d336c1609eced93c
Witnessed: Not yet
Weight files: 3
Model size: 1.8 GB
Downloads · last month: 546
Publisher: Unclaimed

Public checksum record coming on the next sync