Long-context variant (max_seq_length=8192). Recommended for long scientific inputs; best within-recipe scores on the Body-Fact Retrieval probe and LongEmbed.
A 149M-parameter ModernBERT-base scientific document embedder trained with citation-context sentences as the primary contrastive signal. Part of the
SciEmbed
release (paper under double-blind review; author info omitted).
Usage
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("anon-nlp/sciembed-ctx-8192")
emb = model.encode(["citation-context supervision for scientific embeddings"],
normalize_embeddings=True)
Context length:
8192 tokens
Pooling:
mean ·
Output dim:
768 (Matryoshka-truncatable to 512/256/128)
License:
MIT
Citation
See the repository README. Paper:
SciEmbed: Citation-Context Supervision for Scientific Document Embeddings
(under review).
Runs of anon-nlp sciembed-ctx-8192 on huggingface.co
84
Total runs
-15
24-hour runs
-1
3-day runs
3
7-day runs
-5
30-day runs
More Information About sciembed-ctx-8192 huggingface.co Model
sciembed-ctx-8192 huggingface.co is an AI model on huggingface.co that provides sciembed-ctx-8192's model effect (), which can be used instantly with this anon-nlp sciembed-ctx-8192 model. huggingface.co supports a free trial of the sciembed-ctx-8192 model, and also provides paid use of the sciembed-ctx-8192. Support call sciembed-ctx-8192 model through api, including Node.js, Python, http.
sciembed-ctx-8192 huggingface.co is an online trial and call api platform, which integrates sciembed-ctx-8192's modeling effects, including api services, and provides a free online trial of sciembed-ctx-8192, you can try sciembed-ctx-8192 online for free by clicking the link below.
anon-nlp sciembed-ctx-8192 online free url in huggingface.co:
sciembed-ctx-8192 is an open source model from GitHub that offers a free installation service, and any user can find sciembed-ctx-8192 on GitHub to install. At the same time, huggingface.co provides the effect of sciembed-ctx-8192 install, users can directly use sciembed-ctx-8192 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.