DuyTa/sec-embedding

Model card: add acceptance (nghiệm thu) LLM/quality/task KPIs, training set size & hardware

Update model card: set license to apache-2.0; add acceptance (nghiệm thu) model info & KPIs

Model card: fine-tuned BGE-M3 dense retriever (Qdrant CVE hard-negative trajectories)

Restore model card: BGE-M3 contrastive LoRA fine-tune on Qdrant CVE trajectories

Revert README to honest re-host description (no unverified fine-tune claim)

Update model card: contrastive LoRA fine-tune on Qdrant CVE trajectories

Re-host BAAI/bge-m3 as sec-embedding for secAI pipeline

initial commit