33.36M BERT scale
Captured config identifies BertModel and Safetensors metadata reports 33360512 parameters.
Open Source Model Profile · thenlper
gte-small
gte-small is a 33.36M-parameter BERT embedding model from thenlper. According to the model card, it belongs to the GTE family for retrieval and similarity work.
- Publisher
- thenlper
- Task
- sentence-similarity
- Model type
- bert
- License
- mit
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
gte-small is published by thenlper as a bert-based sentence-similarity model. The captured configuration identifies BertModel, and Safetensors metadata reports 33360512 parameters. According to the model card, it is a General Text Embeddings model in a family trained by Alibaba DAMO Academy on relevance text pairs.
Recorded capabilities
384-dimension embeddings
According to the model card, the model uses 384 dimensions with a 512 sequence length and 0.07GB size.
MTEB-reported GTE family
The card places gte-small in the GTE family and reports an MTEB average of 61.36 alongside retrieval, STS, reranking, and classification figures.
Use cases in the source record
- Information retrieval, semantic textual similarity, and text reranking experiments the publisher lists as GTE downstream tasks.
Limitations and unknowns
- No independently measured evaluation results were extracted; MTEB figures are publisher-reported card claims.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: thenlper/gte-small
Captured: Unknown. Processed: 2026-09-07T19:35:00.253180+00:00.
gte-small General Text Embeddings (GTE) model. Towards General Text Embeddings with Multi-stage Contrastive Learning The GTE models are trained by Alibaba DAMO Academy. They are mainly based on the BERT framework and currently offer three different sizes of models, including GTE-large , GTE-base , and GTE-small . The GTE models are trained on a large-scale corpus of relevance text pairs, covering a wide range of domains and scenarios. This enables the GTE models to be applied to various downstream tasks of text embeddings, including information retrieval , semantic textual similarity , text reranking , etc. Metrics We compared the p…
F001F002F003F004F005F006F007F010F011F012F013F014