pip install transformers torch

import torch
from transformers import AutoTokenizer, AutoModelForSequenceClassification

model_name = "zenlm/zen-reranker-4B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(
    model_name, 
    torch_dtype=torch.float16
)

def rerank(query, passages):
    """Score and rank passages by relevance to query."""
    pairs = [[query, p] for p in passages]
    inputs = tokenizer(
        pairs, 
        padding=True, 
        truncation=True,
        max_length=512, 
        return_tensors="pt"
    )
    
    with torch.no_grad():
        scores = model(**inputs).logits.squeeze(-1)
    
    ranked = sorted(
        zip(passages, scores.tolist()), 
        key=lambda x: x[1], 
        reverse=True
    )
    return ranked

# Example usage
query = "What are the benefits of renewable energy?"
passages = [
    "Wind and solar power reduce carbon emissions and provide clean electricity.",
    "Coal is still the most abundant fuel source worldwide.",
    "Renewable energy reduces dependence on fossil fuels and lowers costs long-term."
]

results = rerank(query, passages)
for passage, score in results:
    print(f"{score:.3f}: {passage}")

from sentence_transformers import CrossEncoder

model = CrossEncoder("zenlm/zen-reranker-4B")

pairs = [
    ["What are renewable energy benefits?", "Wind power reduces emissions."],
    ["What are renewable energy benefits?", "Coal is abundant worldwide."],
    ["What are renewable energy benefits?", "Solar lowers long-term costs."],
]

scores = model.predict(pairs)

for pair, score in zip(pairs, scores):
    print(f"{score:.3f}: {pair[0]} | {pair[1]}")

curl -X POST https://api.hanzo.ai/v1/chat/completions \
  -H "Authorization: Bearer $ZEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen-reranker-4b",
    "messages": [...]
  }'