Downloads · 30 days
37
38% of all-time downloads
thu-nmrc/bge-small-structural-separator
bge-small-structural-separator is a feature extraction model from thu-nmrc. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as mit.
This is the complete Transformers checkpoint for the H216 Shared Structural Separator Field Encoder. It is compatible with AutoModel and AutoTokenizer.
Downloads · 30 days
37
38% of all-time downloads
All-time downloads
97
Public
Parameters
33.4M
133 MB on disk
Likes
2
Public
Click a slice to open those files.
.safetensors133 MB · 99%
From the Hugging Face model README
This is the complete Transformers checkpoint for the H216 Shared Structural
Separator Field Encoder. It is compatible with AutoModel and AutoTokenizer.
H216 starts from the immutable
BAAI/bge-small-en-v1.5@5c38ec7c405ec4b44b94cc5a9bb96e735b38267a
checkpoint and learns exactly one 384-value input-embedding row: token
[unused2], vocabulary ID 3. All other model parameters are unchanged.
Document formatting inserts [unused2] before a nonempty title and before each
punctuation-delimited sentence. The document is encoded once and its normalized
CLS vector is stored. Queries use ordinary tokenizer formatting with no
instruction. Retrieval is exact cosine over one query vector and one document
vector; there is no fusion, routing, reranking, expansion, or protected
candidate frontier.
from transformers import AutoModel, AutoTokenizer
model_id = "thu-nmrc/bge-small-structural-separator"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModel.from_pretrained(model_id)
The repository includes separator_row.pt, the deterministic training manifest,
and export_manifest.json with SHA-256 hashes for the complete checkpoint.
Training used 4,096 S2ORC citation-context/abstract pairs and no BEIR labels,
validation selection, benchmark negative mining, or post-training tuning.
The bounded research claim is a learned document-side structural separator adaptation within the dense bi-encoder family. It is not claimed as a replacement for all dense retrievers. Full evaluation details, training code, overlap audits, and disclosed regressions are maintained at https://github.com/thu-nmrc/bge-small-structural-separator.
The frozen BEIR8 gate improves macro NDCG@10 by +0.012705 over the matched plain
BGE control. A later preregistered six-task MTEB(eng, v2) Retrieval extension
does not support broad transfer: macro NDCG@10 changes by -0.011038 and H216 wins
two of six tasks. Across all ten official Retrieval tasks the macro delta is
+0.002855, but claims remain bounded to the BEIR8 structure-native evidence.