Model reference · open weights
modernbert-tr-reranker is an open-weight embedding model from ytu-ce-cosmos, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
A 150M-parameter Turkish cross-encoder reranker to score (query, document) relevance. - Base model: ytu-ce-cosmos/modernbert-tr-base. - Distilled from Qwen/Qwen3-Reranker-8B. Results Reranking the top-100 of a first-stage retriever (ytu-ce-cosmos/modernbert-tr-embed) at maxseq=512. The uplift (Δ) is the reranker's contribution. How was this model trained? Question answering and counter argument distillation of Qwen3-Reranker-8B relevance scores into the 150M cross-encoder over Turkish question answering / information retrieval data using listwise KL. Usage transformers sentence-transformers ONNX Runtime The onnx/ folder has the full graph, the output is the relevance logit: Text Embeddings Inference (TEI) Training data We used Turkish datasets msmarco-tr, squad-tr, fiqa-tr, nfcorpus-tr, quora-tr, scifact-tr for distillation by Qwen3-Reranker-8B, and Turkish counter-argument pairs from ArguAna machine-translated with TranslateGemma-27B. All training data was text-hash chceked against every MTEB(Turkish) test split. Limitations - Reported NDCG is rerank-of-top-100 over a first-stage retriever; absolute scores depend on that first stage. - int8 ONNX reorders scores meaningfully lossy for a reranker; use fp32 for quality-sensitive ranking. - Due to the lack of long form data in our training, the model's performance may degrade on long context input. License & attribution - License: apache-2.0.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | ytu-ce-cosmos |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 149M |
| Context | 8k tokens |
| Variants | 1 |
| Runs with | transformers |
| Based on | ytu-ce-cosmos/modernbert-tr-base |
| Released | 2026-06-30 |
| Popularity | 18k downloads / month |
| Likes | 3 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| modernbert-tr-reranker | 149M | BF16 | ~0.3 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| ArguAnaTR | MTEB ArguAnaTR | ndcg_at_10 | 54.75 |
| CQADupstackGamingRetrievalTR | MTEB CQADupstackGamingRetrievalTR | ndcg_at_10 | 61.1 |
| SciFactTR | MTEB SciFactTR | ndcg_at_10 | 86.34 |
| SquadTRRetrieval | MTEB SquadTRRetrieval | ndcg_at_10 | 90.11 |
| TQuadRetrieval | MTEB TQuadRetrieval | ndcg_at_10 | 94 |
| XQuADRetrieval | MTEB XQuADRetrieval | ndcg_at_10 | 97.86 |
Using it via the API
Once AxForge deploys modernbert-tr-reranker for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (modernbert-tr-reranker below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"modernbert-tr-reranker","input":"text to embed"}'
Details
Languages
Tags
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore