Model card: fine-tuned Qwen3 listwise generative reranker (Qdrant CVE hard negatives)

README.md

@@ -7,6 +7,7 @@ pipeline_tag: text-ranking
 language:
   - en
   - vi
+pretty_name: sec-rerank (fine-tuned Qwen3-Reranker)
 tags:
   - reranker
   - cross-encoder
@@ -21,48 +22,48 @@ tags:
 
 # sec-rerank
 
-Domain-adapted **listwise generative reranker** for CVE / cybersecurity search. Fine-tuned from [Qwen/Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B) (Apache-2.0) on grouped query–document examples whose **hard negatives were mined from a local Qdrant** collection (`cve_kb`).
+**This is a fine-tuned version of [Qwen/Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B)** — a **listwise generative reranker** (second-stage ranker), not an embedding model.
 
-This is a **second-stage ranker**, not an embedding model. It does not produce dense vectors. It reorders first-stage retrieval candidates (e.g. from [`DuyTa/sec-embedding`](https://huggingface.co/DuyTa/sec-embedding)) by scoring each `(query, document)` pair with the native Qwen3-Reranker generative head.
+It was trained on grouped query–document examples whose **hard negatives were mined from a local Qdrant** collection (`cve_kb`) built from CVE investigation trajectories. It does not emit dense vectors; it reorders first-stage candidates (e.g. from [`DuyTa/sec-embedding`](https://huggingface.co/DuyTa/sec-embedding)).
 
 ## Training
 
-Recipe follows the secAI Colab trainer (`notebooks/Qwen3_Reranker_Colab.ipynb`):
+From `notebooks/Qwen3_Reranker_Colab.ipynb` (ms-swift):
 
 | | |
 |---|---|
 | Base | `Qwen/Qwen3-Reranker-0.6B` |
-| Task | SWIFT `generative_reranker` (causal-LM reranker, not a bi-encoder) |
+| Task | `generative_reranker` (causal-LM reranker / cross-encoder scoring) |
 | Loss | **listwise reranking** (`--loss_type listwise_reranker`) |
 | Tuner | full-parameter SFT (`--tuner_type full`) |
 | Engine | [ms-swift](https://github.com/modelscope/ms-swift) `swift sft` |
 | Max length | 2048 |
 | Learning rate | 6e-6 |
 
-Project `(query, positive, negative)` rows are converted to SWIFT's **grouped ranking** schema before training:
+`(query, positive, negative)` rows are converted to SWIFT **grouped ranking** schema:
 
 - `messages` — system instruction + user query
 - `positive_messages` — gold CVE passage
-- `negative_messages` — hard-negative CVE passage(s)
+- `negative_messages` — Qdrant-mined hard-negative CVE passage(s)
 
-Instruction used at train time:
+Train-time instruction:
 
 > Given a Vietnamese cybersecurity search query, retrieve passages from the CVE knowledge base that directly answer it.
 
-SWIFT fills the native Qwen3-Reranker `{Instruction}` slot from that system message. Do not inject `<|im_start|>` or `<think>` into the JSONL.
+SWIFT fills the native Qwen3-Reranker `{Instruction}` slot from that system message.
 
 ### Hard-negative mining
 
-Positives and negatives are real CVE core-chunk text from the local Qdrant `cve_kb` (NVD/MITRE). For each query, the negative is a **near-miss CVE** from the same collection — typically a different CWE (`hard_negative_type: different_cwe`) so lexical overlap is high but the relevant document is wrong. That is the listwise signal: rank the gold passage above mined hard negatives for the same query.
+Positives and negatives are real CVE core-chunk text from local Qdrant `cve_kb` (NVD/MITRE). The negative is a **near-miss CVE** from the same collection — typically a different CWE (`hard_negative_type: different_cwe`): high lexical overlap, wrong document. The listwise objective ranks the gold passage above those mined hard negatives.
 
-Full split is 33.6k train / 4.2k validation grouped examples.
+Split: 33.6k train / 4.2k validation grouped examples.
 
 ## Inference
 
-Keep the Qwen3-Reranker prompt format. The model scores a candidate by the generative yes/no head; higher score = more relevant. Use it only to **rerank** a short candidate list from dense / hybrid retrieval, not as a first-stage embedder.
+Score each `(query, document)` with the native Qwen3-Reranker generative yes/no head. Use only to **rerank** a short candidate list from dense / hybrid retrieval.
 
 ```python
-# vLLM / OpenAI-compatible rerank endpoint (secAI serving stack)
+# vLLM / OpenAI-compatible rerank endpoint
 # POST /v1/rerank
 {
   "model": "DuyTa/sec-rerank",
@@ -73,4 +74,4 @@ Keep the Qwen3-Reranker prompt format. The model scores a candidate by the gener
 
 ## Attribution & license
 
-Weights derive from [Qwen/Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B), released under **Apache-2.0**. All credit for the base reranker belongs to the Qwen team. This card and the Qdrant listwise fine-tune are part of the secAI retrieval stack.
+Derived from [Qwen/Qwen3-Reranker-0.6B](https://huggingface.co/Qwen/Qwen3-Reranker-0.6B) (**Apache-2.0**). Credit for the base reranker belongs to the Qwen team.