BERT embedding configuration
Captured configuration identifies BertModel with a bert model type, about 109M parameters, and a sentence-transformers library tag.
Open Source Model Profile · thenlper
gte-base
gte-base is a 109M-parameter BERT-family sentence-similarity embedding model from thenlper. The model card describes it as a General Text Embeddings (GTE) model.
- Publisher
- thenlper
- Task
- sentence-similarity
- Model type
- bert
- License
- mit
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
gte-base is published by thenlper as a sentence-similarity embedding model. The captured configuration identifies BertModel with a bert model type and Safetensors metadata reports 109482752 parameters. According to the model card, it is a General Text Embeddings (GTE) model in a family described as trained by Alibaba DAMO Academy.
Recorded capabilities
768-dimension embeddings
According to the model card, gte-base uses 768 dimensions with 512 sequence length and a 0.22 GB model size.
GTE training description
According to the model card, the GTE models were trained by Alibaba DAMO Academy on a large-scale corpus of relevance text pairs for retrieval, semantic textual similarity, and reranking uses.
Publisher-reported MTEB table
The model card points to the MTEB leaderboard and includes a comparison table reporting 62.39 average for gte-base.
Use cases in the source record
- Text-embedding workflows for information retrieval using sentence-similarity representations.
- According to the model card, semantic textual similarity and text reranking tasks covered by the GTE training description.
Limitations and unknowns
- No independent Ethen evaluation results were extracted from this record; benchmark figures come from the publisher model card.
- No context-window value was extracted from this record.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Training and origin information comes from the publisher model card and has not been independently verified by Ethen.
Source and provenance
Source: thenlper/gte-base
Captured: Unknown. Processed: 2026-09-07T19:34:59.703633+00:00.
gte-base 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 pe…
F001F002F003F004F005F006F007F008F010F011F012F013F014