Text Ranking
Transformers
Safetensors
sentence-transformers
qwen3
text-generation
cross-encoder
reranker
Instructions to use ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b") model = AutoModelForCausalLM.from_pretrained("ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b", device_map="auto") - sentence-transformers
How to use ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b") query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Notebooks
- Google Colab
- Kaggle
Download chat_template.jinja from ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b: direct link, hf CLI and curl.
- Browser
- Download file 540 Bytes
-
https://huggingface.co/ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b/resolve/main/chat_template.jinja
- Command line
-
hf download hf://ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b/chat_template.jinja
-
curl -L -o chat_template.jinja https://huggingface.co/ContextualAI/ctxl-rerank-v2-instruct-multilingual-2b/resolve/main/chat_template.jinja
540 Bytes
| {%- set instruction_text = messages | selectattr("role", "eq", "system") | map(attribute="content") | first | default("") -%} | |
| {%- set query_text = messages | selectattr("role", "eq", "query") | map(attribute="content") | first -%} | |
| {%- set document_text = messages | selectattr("role", "eq", "document") | map(attribute="content") | first -%} | |
| Check whether a given document contains information helpful to answer the query. | |
| <Document> {{ document_text }} | |
| <Query> {{ query_text }}{% if instruction_text %} {{ instruction_text }}{% endif %} ?? |