# HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5

Model from Hugging Face for sentence similarity: HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5 · sentence transformers

## Facts

- Type: Embedding
- Task: sentence-similarity
- Framework: sentence-transformers
- License: mit — Permissive open license: commercial use, modification, and redistribution are permitted. (https://spdx.org/licenses/MIT.html)
- Source: https://huggingface.co/HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5
- Hosting: hosted (13 files)
- Files: 13 hosted of 15 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: 1.99 GB
- Recommended file: 1.98 GB · model.safetensors
- Download: https://huggingbay.xyz/artifact/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/files (download plan: https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/download-plan)
- Per-file SHA-256: available for 13 of 13 hosted files via https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/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: 4463
- Stars: 66
- Card completeness: 94%

## Description

External Hugging Face catalog record for HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5. Task: sentence similarity. Library: sentence transformers. Includes 12 model-card evaluation signals. Popularity signal at import: 1,553 downloads and 66 likes.

## Model Card Facts

- Declared license: mit
- Pipeline: sentence-similarity
- Library: sentence-transformers
- Task categories: sentence-similarity
- Paper ids: 2501.01028
- Model-index entries: KaLM-Embedding
- Evaluation signals: 12 model-card eval results
- File hints: 15 upstream file samples

## Evaluation Signals

- MTEB AmazonCounterfactualClassification (en-ext): accuracy = 94.68515742128936 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): ap = 61.63091951041035 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): ap_weighted = 61.63091951041035 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): f1 = 87.0707144798333 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): f1_weighted = 94.92507672044346 (Classification)
- MTEB AmazonCounterfactualClassification (en-ext): main_score = 94.68515742128936 (Classification)
- MTEB AmazonCounterfactualClassification (en): accuracy = 91.73134328358209 (Classification)
- MTEB AmazonCounterfactualClassification (en): ap = 68.35026743834399 (Classification)
- MTEB AmazonCounterfactualClassification (en): ap_weighted = 68.35026743834399 (Classification)
- MTEB AmazonCounterfactualClassification (en): f1 = 87.90511074439425 (Classification)

## Referenced Data

- Paper: 2501.01028

## File Hints

- .gitattributes (1.5 KB)
- 1_Pooling/config.json (296 B)
- README.md (587 KB)
- added_tokens.json (80 B)
- config.json (655 B)
- config_sentence_transformers.json (208 B)
- merges.txt (1.6 MB)
- model.safetensors (1.8 GB) LFS
- modules.json (349 B)
- sentence_bert_config.json (55 B)
- special_tokens_map.json (370 B)
- tokenization_qwen.py (11 KB)

## 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 2026-08-29T01:29:55.459Z.
- Open license detected as mit.
- Model-index metadata found for KaLM-Embedding.
- 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-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5
- Files API: https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/files?limit=100
- Metadata: https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/metadata.json
- Distribution: https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/distribution
- Manifest: https://huggingbay.xyz/api/manifests/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5
- Download plan (per-file SHA-256 + signed download URLs): https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/download-plan
- Hosted download rows: https://huggingbay.xyz/api/downloadable-files?artifactId=hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5&limit=100
- Request mirror: not applicable.
- Submit peer fallback for review: POST https://huggingbay.xyz/api/artifacts/hf-model-hit-tmg-kalm-embedding-multilingual-mini-instruct-v1-5/decentralized-fallbacks