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

README.md

@@ -1,5 +1,5 @@
 ---
-license: mit
+license: apache-2.0
 base_model: BAAI/bge-m3
 base_model_relation: finetune
 library_name: sentence-transformers
@@ -18,13 +18,16 @@ tags:
   - cybersecurity
   - qdrant
   - secAI
+datasets:
+  - DuyTa/Cyber_F1_v2
+  - DuyTa/cve-kgrag-db
 ---
 
 # sec-embedding
 
 **This is a fine-tuned version of [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3)** for CVE / cybersecurity dense retrieval.
 
-It was trained on a **CVE investigation-trajectory dataset** with **hard-negative mining** from a **local Qdrant** collection (`cve_kb`, NVD/MITRE core chunks). It is not a raw copy of the base checkpoint.
+It was trained on a **CVE investigation-trajectory dataset** with **hard-negative mining** from a **local Qdrant** collection (`cve_kb`, NVD/MITRE core chunks). It is not a raw copy of the base checkpoint. It is the retriever component of the **secAI** stack, paired with [`DuyTa/sec-rerank`](https://huggingface.co/DuyTa/sec-rerank) and [`DuyTa/Cyber-F1-AWQ`](https://huggingface.co/DuyTa/Cyber-F1-AWQ).
 
 ## Training
 
@@ -48,6 +51,21 @@ Each example is a `(query, positive)` pair:
 
 Dataset source field: `Qdrant cve_kb (NVD/MITRE)`. Split: 40k train / 5k validation.
 
+### Training corpus
+
+Built from **five years of authoritative cybersecurity sources**: NVD (173,473 CVEs), MITRE CWE (768 weakness types, mapped to ~92% of CVEs), CAPEC/ATT&CK (443/174 entries) and Exploit-DB (3,139 exploits, 2021–2026). Public datasets: [`DuyTa/Cyber_F1_v2`](https://huggingface.co/datasets/DuyTa/Cyber_F1_v2), [`DuyTa/cve-kgrag-db`](https://huggingface.co/datasets/DuyTa/cve-kgrag-db).
+
+## Acceptance (nghiệm thu) — reported KPIs
+
+Measured on **NVIDIA A100 80GB** in the full production chatflow (Hybrid Search → Rerank → LLM), on a 1,000-sample security test set (40% CVE identification/classification, 40% remediation advice, 20% real-world scenario reasoning):
+
+| Metric | Result | Target | Pass |
+|---|---|---|---|
+| Retrieval quality — **Hit Rate@10** | **98.78%** | > 96% | ✅ |
+| Throughput | **2,662 emb/s** (concurrency 32) | ≥ 1,200 emb/s | ✅ |
+
+Raw per-sample logs (`embedding-hit-rate-at-10.jsonl`) and evaluation code are delivered with the acceptance package.
+
 ## Usage
 
 ```python
@@ -62,4 +80,4 @@ Rebuild the Qdrant index with **this** checkpoint. Mixing vectors with vanilla `
 
 ## Attribution & license
 
-Derived from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) (**MIT License**). Credit for the base model belongs to the BAAI authors.
+Released under **Apache-2.0**. Derived from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) (**MIT License**); the MIT notice of the base model is retained and credit for the base weights belongs to the BAAI authors.