MMLForge Search models, datasets, tasks… Start free
Home › Models › Sentence Similarity › HIT-TMG/KaLM-embedding-multilingual-mini-v1
K

HIT-TMG/KaLM-embedding-multilingual-mini-v1

Sentence Similarity·HIT-TMG· 86.2K· 31
sentence-transformers mit Sentence Similarity 494.0M params arxiv:2501.01028license:mitdeploy:azure

KaLM-Embedding is a series of embedding models adapted from auto-regressive LLMs with superior training data.

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull HIT-TMG/KaLM-embedding-multilingual-mini-v1

Model details

Task
Sentence Similarity
Provider
HIT-TMG
Framework
sentence-transformers
Parameters
494.0M
Size
1.8 GB
License
mit
Downloads
86.2K
Likes
31
Paper
arXiv:2501.01028
Updated
2025-01-03

About HIT-TMG/KaLM-embedding-multilingual-mini-v1

--- license: mit model-index: - name: KaLM-Embedding results: - dataset: config: en-ext name: MTEB AmazonCounterfactualClassification (en-ext) revision: e8379541af4e31359cca9fbcf4b00f2671dba205 split: test type: mteb/amazoncounterfactual metrics: - type: accuracy value: 74.16041979010495 - type: ap value: 22.731316107205824 - type: apweighted value: 22.731316107205824 - type: f1 value: 61.311184650259634 - type: f1weighted value: 78.92070802470501 - type: mainscore value: 74.16041979010495 task: type: Classification - dataset: config: en name: MTEB AmazonCounterfactualClassification (en) revision: e8379541af4e31359cca9fbcf4b00f2671dba205 split: test type: mteb/amazoncounterfactual metrics: - type: accuracy value: 72.35820895522387 - type: ap value: 34.13026440006763 - type: apweighted value: 34.13026440006763 - type: f1 value: 65.91101941691169 - type: f1weighted value: 74.90947851184335 - type: mainscore value: 72.35820895522387 task: type: Classification - dataset: config: default name: MTEB AmazonPolarityClassification revision: e2d317d38cd51312af73b3d32a06d1a08b442046 split: test type: mteb/amazonpolarity metrics: - type: accuracy value: 95.2693 - type: ap value: 93.69278757537118 - type: apweighted value: 93.69278757537118 - type: f1 value: 95.26705627226383 - type: f1weighted

Related Sentence Similarity

A sentence-transformers/all-MiniLM-L6-v2 Sentence Similarity ·22.7M params 255.4M 5.0K 🤗 HF P sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 Sentence Similarity ·117.7M params 50.8M 1.3K 🤗 HF A sentence-transformers/all-mpnet-base-v2 Sentence Similarity ·109.5M params 33.9M 1.3K 🤗 HF B BAAI/bge-m3 Sentence Similarity 31.1M 3.1K 🤗 HF N nomic-ai/nomic-embed-text-v1.5 Sentence Similarity ·136.7M params 18.3M 856 🤗 HF M intfloat/multilingual-e5-small Sentence Similarity ·117.7M params 10.0M 344 🤗 HF

Browse all Sentence Similarity models →