Alibaba-NLP/gte-large-en-v1.5
We introduce gte-v1.5 series, upgraded gte embeddings that support the context length of up to 8192, while further enhancing model performance. The models are built upon the transformer++ encoder backbone (BERT + RoPE + GLU).
pip install mlforge-sdk && mlforge pull Alibaba-NLP/gte-large-en-v1.5
Model details
About Alibaba-NLP/gte-large-en-v1.5
--- datasets: - allenai/c4 libraryname: transformers tags: - sentence-transformers - gte - mteb - transformers.js - sentence-similarity license: apache-2.0 language: - en model-index: - name: gte-large-en-v1.5 results: - task: type: Classification dataset: type: mteb/amazoncounterfactual name: MTEB AmazonCounterfactualClassification (en) config: en split: test revision: e8379541af4e31359cca9fbcf4b00f2671dba205 metrics: - type: accuracy value: 73.01492537313432 - type: ap value: 35.05341696659522 - type: f1 value: 66.71270310883853 - task: type: Classification dataset: type: mteb/amazonpolarity name: MTEB AmazonPolarityClassification config: default split: test revision: e2d317d38cd51312af73b3d32a06d1a08b442046 metrics: - type: accuracy value: 93.97189999999999 - type: ap value: 90.5952493948908 - type: f1 value: 93.95848137716877 - task: type: Classification dataset: type: mteb/amazonreviewsmulti name: MTEB AmazonReviewsClassification (en) config: en split: test revision: 1399c76144fd37290681b995c656ef9b2e06e26d metrics: - type: accuracy value: 54.196 - type: f1 value: 53.80122334012787 - task: type: Retrieval dataset: type: mteb/arguana name: MTEB ArguAna config: default split: test revision: c22ab2a51041ffd869aaddef7af8d8215647e41a metrics: - type: mapat1 value: 47.297 - type: mapat10 value: