stella-mrl-large-zh-v3.5-1792d

Model overview

stella-mrl-large-zh-v3.5-1792d is published by dunzhang as a sentence-similarity model. Captured Safetensors metadata reports 325,522,432 parameters, about 326M. According to the model card, the open puff-series model targets retrieval and semantic matching with attention to generalization and variable-dimension vectors in Chinese and English.

Recorded capabilities

Use cases in the source record

• Bilingual retrieval and semantic-matching workloads using the model's variable-dimension vectors.

Limitations and unknowns

• No evaluation results were extracted from this record.
• No training data, compute, or hyperparameter detail was extracted from this record.
• No embedding dimensions or context-window value was extracted from this record.
• Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: dunzhang/stella-mrl-large-zh-v3.5-1792d

Captured: Unknown. Processed: 2026-09-07T19:34:43.783469+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！ 1 开源模型 本次开源stella-mrl-large-zh-v3.5-1792d模型， 本模型是在stella-large-zh-v3-1792d的基础上使用 MRL 方法训练而成。 其主要特点是 可变的向量维度 。 2 使用方法 from sentence_transformers import SentenceTransformer from sklearn.preprocessing import normalize model = SentenceTransformer( "inf…