Text Ranking
Transformers
Safetensors
English
Vietnamese
qwen3
text-generation
reranker
cross-encoder
listwise-reranking
generative-reranker
cve
cybersecurity
qdrant
secAI
Instructions to use DuyTa/sec-rerank with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DuyTa/sec-rerank with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DuyTa/sec-rerank") model = AutoModelForCausalLM.from_pretrained("DuyTa/sec-rerank", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| {%- set instruction = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("Given a web search query, retrieve relevant passages that answer the query") -%} | |
| {%- set query_text = messages | selectattr("role", "eq", "query") | map(attribute="content") | first -%} | |
| {%- set document_text = messages | selectattr("role", "eq", "document") | map(attribute="content") | first -%} | |
| <|im_start|>system | |
| Judge whether the Document meets the requirements based on the Query and the Instruct provided. Note that the answer can only be "yes" or "no".<|im_end|> | |
| <|im_start|>user | |
| <Instruct>: {{ instruction }} | |
| <Query>: {{ query_text }} | |
| <Document>: {{ document_text }}<|im_end|> | |
| <|im_start|>assistant | |
| <think> | |
| </think> | |