BERT sentence-transformers build
Captured config identifies BertModel, and hub tags list the sentence-transformers library with feature-extraction and sentence-similarity.
Open Source Model Profile · infgrad
stella-base-en-v2
stella-base-en-v2 is an English feature-extraction embedding model from infgrad. Its model card documents a 768-dimension entry with contrastive training notes.
- Publisher
- infgrad
- Task
- feature-extraction
- Model type
- bert
- License
- mit
- Library
- sentence-transformers
- Publication status
- Accepted · not indexed
Model overview
stella-base-en-v2 is published by infgrad as a feature-extraction embedding model. The captured configuration identifies BertModel with a bert model type and a sentence-transformers library tag. According to the model card, the stella-base-en-v2 entry covers English with 768 dimensions.
Recorded capabilities
Listed 768-dimension English entry
According to the model card, the stella-base-en-v2 row lists 768 dimensions with English coverage.
Documented contrastive training
The card describes contrastive and hard-negative loss functions, knowledge-distillation instruction removal, and expanded v2 training data.
Publisher-reported MTEB values
According to the model card, self-reported MTEB figures include AmazonCounterfactualClassification and AmazonPolarityClassification values.
Use cases in the source record
- English sentence-embedding and semantic-similarity workflows that use the sentence-transformers stack.
- Retrieval experiments that use the documented 768-dimension vectors and contrastive-training setup.
Limitations and unknowns
- No parameter count was extracted from this record.
- No context-window value was extracted from this record.
- Evaluation figures are publisher-reported, self-reported MTEB values and have not been independently verified by Ethen.
- Provider state is historical snapshot data, not independently refreshed current availability.
- Long-text benchmark comparisons and training-data quality caveats come from the publisher card and should be read as publisher analysis, not Ethen findings.
Source and provenance
Source: infgrad/stella-base-en-v2
Captured: Unknown. Processed: 2026-09-07T19:34:47.200696+00:00.
新闻 | News [2024-04-06] 开源 puff 系列模型， 专门针对检索和语义匹配任务，更多的考虑泛化性和私有通用测试集效果，向量维度可变，中英双语 。 [2024-02-27] 开源stella-mrl-large-zh-v3.5-1792d模型，支持 向量可变维度 。 [2024-02-17] 开源stella v3系列、dialogue编码模型和相关训练数据。 [2023-10-19] 开源stella-base-en-v2 使用简单， 不需要任何前缀文本 。 [2023-10-12] 开源stella-base-zh-v2和stella-large-zh-v2, 效果更好且使用简单， 不需要任何前缀文本 。 [2023-09-11] 开源stella-base-zh和stella-large-zh 欢迎去 本人主页 查看最新模型，并提出您的宝贵意见！ stella model stella是一个通用的文本编码模型，主要有以下模型： Model Name Model Size (GB) Dimension Sequence Length Language Need instruction for retrieval? stella-base-en-v2 0.2 768 512 English No stella-large-zh-v2 0.65 1024 1024 Chinese No stella-base-zh-v2 0.2 768 1…
F001F002F003F004F005F006F007F008F009F014F015F017F018F019F020