Model reference · open weights

stella-mrl-large-zh-1792d

Embeddings dunzhang Embeddings 1 build Open weights 103k dl/mo

stella-mrl-large-zh-1792d is an open-weight embedding model from dunzhang. stella-mrl-large-zh-v3.5-1792d (FP32) weighs 651 MB; the smallest configuration that runs it is RTX 3060 12 GB.

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

  • stella-mrl-large-zh-1792d is a 326M parameter sentence-similarity model developed by dunzhang for retrieval and semantic matching tasks.
  • It supports variable vector dimensions up to 1792, a context length of 512 tokens, and is released under the MIT license.

Summary of the dunzhang/stella-mrl-large-zh-v3.5-1792d model card, 2026-10-01

What it is

Released bydunzhang
Released2024-02-27
Parameters326M
VRAM651 MB for the weights

What it runs on

Memory and cards for stella-mrl-large-zh-v3.5-1792d (FP32)

651 MBweights, file size
1.1 GBruntime overhead
CardRunsMemory
RTX 3060 12 GBfits11.6 GB
RTX 4060 Ti 16 GBfits15.4 GB
RTX 3090 24 GBfits23.4 GB
RTX 4090 24 GBfits23.4 GB
RTX 5090 32 GBfits31.0 GB
L40S 48 GBfits44.0 GB
A100 80 GBfits78.2 GB
H100 80 GBfits78.1 GB
RTX PRO 6000 Blackwell 96 GBfits93.8 GB
DGX Spark (GB10) 128 GB unifiedfits107 GB
H200 141 GBfits138 GB
B200 180 GBfits176 GB

From the model card

What dunzhang says about stella-mrl-large-zh-1792d

Read the model card

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("infgrad/stella-mrl-large-zh-v3.5-1792d")
# 注意先不要normalize! 选取前n维后再normalize
vectors = model.encode(["text1", "text2"], normalize_embeddings=False)
print(vectors.shape)  # shape is [2,1792]
# n_dims越大效果越好,但是时空消耗就越大。建议维度选取128的倍数,因为是这么训练的
n_dims = 768
cut_vecs = normalize(vectors[:, :n_dims])

3 不同向量维度的CMTEB得分

stella-mrl-large-zh-v3.5-1792d_1024 代表取前1024维。整体趋势是维度越大效果越好。

ModelRetrievalSTSPairClassificationClassificationRerankingClusteringCMTEB-Score
stella-mrl-large-zh-v3.5-1792d_12870.0162.1787.9970.6766.7753.5567.16
stella-mrl-large-zh-v3.5-1792d_25672.1962.4188.0971.2268.3253.3868.02
stella-mrl-large-zh-v3.5-1792d_38472.7762.4388.2671.3468.3153.8768.25
stella-mrl-large-zh-v3.5-1792d_51273.1162.4588.1671.4668.3253.2868.29
stella-mrl-large-zh-v3.5-1792d_64073.2762.4988.2171.4668.6953.6368.42
stella-mrl-large-zh-v3.5-1792d_76873.3862.588.1971.4968.6453.7768.47
stella-mrl-large-zh-v3.5-1792d_89673.3762.588.1471.5168.4454.1368.49
stella-mrl-large-zh-v3.5-1792d_102473.4362.5188.1671.5268.5953.4368.44
stella-mrl-large-zh-v3.5-1792d_115273.4662.4988.1671.5768.5553.6768.49
stella-mrl-large-zh-v3.5-1792d_128073.4862.5188.1271.5568.4453.7468.48
stella-mrl-large-zh-v3.5-1792d_140873.4862.5188.1471.5868.4653.6968.48
stella-mrl-large-zh-v3.5-1792d_153673.4962.588.1171.5568.554.0668.52
stella-mrl-large-zh-v3.5-1792d_166473.5662.4988.0671.5668.4754.2868.56
stella-mrl-large-zh-v3.5-1792d_179273.5162.4888.0971.5668.4554.3968.56

上述表格中stella-mrl-large-zh-v3.5-1792d_1792的得分为68.56和榜单68.55得分不一致,原因和权重类型有关,小差异请忽略不计。

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

Benchmarks

Reported results

As published on the model card: the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
STSMTEB AFQMCcos_sim_pearson54.338
STSMTEB AFQMCcos_sim_spearman58.855
STSMTEB AFQMCeuclidean_pearson57.570
STSMTEB AFQMCeuclidean_spearman58.855
STSMTEB AFQMCmanhattan_pearson57.559
STSMTEB AFQMCmanhattan_spearman58.845
STSMTEB ATECcos_sim_pearson54.220
STSMTEB ATECcos_sim_spearman58.080
STSMTEB ATECeuclidean_pearson61.646
STSMTEB ATECeuclidean_spearman58.080
STSMTEB ATECmanhattan_pearson61.645
STSMTEB ATECmanhattan_spearman58.081
ClassificationMTEB AmazonReviewsClassification (zh)accuracy46.594
ClassificationMTEB AmazonReviewsClassification (zh)f144.732
STSMTEB BQcos_sim_pearson69.168
STSMTEB BQcos_sim_spearman71.048
STSMTEB BQeuclidean_pearson69.951
STSMTEB BQeuclidean_spearman71.048
STSMTEB BQmanhattan_pearson69.925
STSMTEB BQmanhattan_spearman71.026
ClusteringMTEB CLSClusteringP2Pv_measure43.032
ClusteringMTEB CLSClusteringS2Sv_measure40.416
RerankingMTEB CMedQAv1map89.335
RerankingMTEB CMedQAv1mrr91.346
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms