BAAI/bge-reranker-v2-m3 pass
chat template: not in config · view on Hugging Face ↗
Ingot findings
Static battery clean: safetensors weights, license declared, no template/tokenizer drift detected. Deep battery not yet run. Weights battery: embedding-norm scan over 250002 tokens (F32, 1024-dim) found 27 undertrained candidates, 1 plain-ASCII. Scanned 2026-08-20 (published from a community scan).
low Undertrained tokens in vocabulary (non-ASCII tail)
Embedding-norm scan flagged 27 undertrained tokens (norm < 0.3× the vocabulary median), but 1 decode to plain-ASCII strings, so exposure in English-language pipelines is limited. Behavioral confirmation requires the GPU deep battery.
How to fixruntime guardweight-level
Keep the affected token strings out of the model's input — the scan-derived runtime guard carries this model's exact blocklist.
- Fetch this model's guard artifact (`/api/v1/guard/<owner>/<model>`): the confirmed corrupting tokens and the low-norm candidate list, derived from the published scan.
- Screen inbound text with it (the `@ingotai/guard` package is a reference implementation) and route flagged records to a different model or human review — verbatim-copy tasks on flagged strings are the failure mode.
- The underlying cause is undertrained embeddings in the weights; a true fix is weight-level (continued pretraining on the affected tokens) — that is not a patch, it's a training job.
Remediation guidance addresses the documented findings only. It is evidence-driven repair, not a safety certification of the model.
Fingerprint
The durable weights-and-metadata profile of this model, rebuilt on every scan and deep-battery run. Updated 2026-08-20.
| architecture | xlm-roberta · 24 layers · 1024-dim |
| parameters | 567.8M |
| vocabulary | 250,002 tokens |
| license | apache-2.0 |
| serialization | safetensors |
| chat template | none |
| glitch-token surface | 27 undertrained candidates, 1 plain-ASCII |
Full fingerprint
| architectures | XLMRobertaForSequenceClassification |
| library | sentence-transformers |
| pipeline | text-classification |
| repo files | 13 |
| revision | 953dc6f6f85a |
| HF snapshot | 18.7M downloads · 1.1k likes · updated 2024-06-24 · captured 2026-08-20 |
| embedding tensor | roberta.embeddings.word_embeddings.weight · F32 · 250,002×1024 |
| embedding norms | median 5.1364 · mean 5.1266 |
| lineage check | no claimed base model |
| glitch-token samples | "ment" |
Verdict badge
Ship the verdict in your README — it always shows the latest published analysis:
[](https://ingot.tools/models/BAAI/bge-reranker-v2-m3)