# KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5

Model from Hugging Face for feature extraction: KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5 · sentence transformers

## Facts

- Type: Embedding
- Task: feature-extraction
- Framework: sentence-transformers
- License: apache-2.0 — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/Apache-2.0.html)
- Source: https://huggingface.co/KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5
- Hosting: hosted (13 files)
- Files: 13 hosted of 23 listed
- File counts: "listed" is every file in the source repository; only hosted files download from Hugging Bay, and the download plan lists the files it selects for one download, so its count can differ.
- Hosted here: 13 files, 1.99 GB
- Full repo upstream: 2 GB
- Recommended file: 1.98 GB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/download-plan)
- Per-file SHA-256: available for 13 of 13 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/files?limit=100
- Run-ready: no (Hugging Bay has not certified a run path for this model; hosted bytes are downloadable and hash-checkable only)
- Peer-assisted fallbacks: 0 verified, 0 pending review
- Downloads: 3779
- Stars: 68
- Card completeness: 96%

## Description

External Hugging Face catalog record for KaLM-Embedding/KaLM-embedding-multilingual-mini-instruct-v2.5. Task: feature extraction. Library: sentence transformers. Languages: en, zh. Datasets referenced by card metadata: HIT-TMG/KaLM-embedding-pretrain-data, KaLM-Embedding/KaLM-embedding-finetuning-data. Popularity signal at import: 2,093 downloads and 68 likes.

## Model Card Facts

- Declared license: apache-2.0
- Pipeline: feature-extraction
- Library: sentence-transformers
- Task categories: feature-extraction
- Languages: en, zh
- Referenced datasets: HIT-TMG/KaLM-embedding-pretrain-data, KaLM-Embedding/KaLM-embedding-finetuning-data
- Paper ids: 2506.20923, 2501.01028
- File hints: 16 upstream file samples

## Referenced Data

- Dataset: HIT-TMG/KaLM-embedding-pretrain-data
- Dataset: KaLM-Embedding/KaLM-embedding-finetuning-data
- Paper: 2506.20923
- Paper: 2501.01028

## File Hints

- .gitattributes (2.0 KB)
- 1_Pooling/config.json (296 B)
- README.md (9.5 KB)
- added_tokens.json (80 B)
- config.json (759 B)
- config_sentence_transformers.json (320 B)
- imgs/archi.jpg (148 KB) LFS
- imgs/logo.jpg (158 KB) LFS
- imgs/matry.jpg (427 KB) LFS
- imgs/mteb_cmn.jpg (430 KB) LFS
- imgs/mteb_eng.jpg (562 KB) LFS
- imgs/ood.jpg (377 KB) LFS

## Quality Checklist

- Summary: passed
- Description: passed
- Model card metadata: passed
- License: passed
- Provenance: passed
- File inventory: passed
- Hosted bytes: passed
- Scan result: passed
- Manifest signature: passed

## Safety Notes

- External catalog metadata imported from Hugging Face public API on 2026-08-29T07:10:29.574Z.
- Open license detected as apache-2.0.
- Model card references dataset context: HIT-TMG/KaLM-embedding-pretrain-data, KaLM-Embedding/KaLM-embedding-finetuning-data.
- Not a run kit: hosted, hash-checked bytes only; run readiness is not certified for this model yet.

## Actions

- Web: https://huggingbay.xyz/artifact/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-kalm-embedding-kalm-embedding-multilingual-mini-instruct-v2-5/decentralized-fallbacks
