Qwen3-Reranker-4B

pip install sentence_transformers

from sentence_transformers import CrossEncoder

model = CrossEncoder("Qwen/Qwen3-Reranker-4B")

query = "What is the capital of China?"
documents = [
    "The capital of China is Beijing.",
    "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun.",
]

pairs = [(query, doc) for doc in documents]
scores = model.predict(pairs)
print(scores)
# [  6.4375 -14.375 ]

rankings = model.rank(query, documents)
print(rankings)
# [{'corpus_id': 0, 'score': 6.4375}, {'corpus_id': 1, 'score': -14.375}]

scores = model.predict([(query, doc) for doc in documents], activation_fn=torch.nn.Sigmoid())

model = CrossEncoder(
    "Qwen/Qwen3-Reranker-4B",
    prompts={"classification": "Classify whether the document matches the query topic"},
    default_prompt_name="classification",
)

KeyError: 'qwen3'

# Requires transformers>=4.51.0
import torch
from transformers import AutoModel, AutoTokenizer, AutoModelForCausalLM

def format_instruction(instruction, query, doc):
    if instruction is None:
        instruction = 'Given a web search query, retrieve relevant passages that answer the query'
    output = "<Instruct>: {instruction}\n<Query>: {query}\n<Document>: {doc}".format(instruction=instruction,query=query, doc=doc)
    return output

def process_inputs(pairs):
    inputs = tokenizer(
        pairs, padding=False, truncation='longest_first',
        return_attention_mask=False, max_length=max_length - len(prefix_tokens) - len(suffix_tokens)
    )
    for i, ele in enumerate(inputs['input_ids']):
        inputs['input_ids'][i] = prefix_tokens + ele + suffix_tokens
    inputs = tokenizer.pad(inputs, padding=True, return_tensors="pt", max_length=max_length)
    for key in inputs:
        inputs[key] = inputs[key].to(model.device)
    return inputs

@torch.no_grad()
def compute_logits(inputs, **kwargs):
    batch_scores = model(**inputs).logits[:, -1, :]
    true_vector = batch_scores[:, token_true_id]
    false_vector = batch_scores[:, token_false_id]
    batch_scores = torch.stack([false_vector, true_vector], dim=1)
    batch_scores = torch.nn.functional.log_softmax(batch_scores, dim=1)
    scores = batch_scores[:, 1].exp().tolist()
    return scores

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-Reranker-4B", padding_side='left')
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Reranker-4B").eval()

# We recommend enabling flash_attention_2 for better acceleration and memory saving.
# model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-Reranker-4B", torch_dtype=torch.float16, attn_implementation="flash_attention_2").cuda().eval()

token_false_id = tokenizer.convert_tokens_to_ids("no")
token_true_id = tokenizer.convert_tokens_to_ids("yes")
max_length = 8192

prefix = "<|im_start|>system\nJudge 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|>\n<|im_start|>user\n"
suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
prefix_tokens = tokenizer.encode(prefix, add_special_tokens=False)
suffix_tokens = tokenizer.encode(suffix, add_special_tokens=False)
        
task = 'Given a web search query, retrieve relevant passages that answer the query'

queries = ["What is the capital of China?",
    "Explain gravity",
]

documents = [
    "The capital of China is Beijing.",
    "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun.",
]

pairs = [format_instruction(task, query, doc) for query, doc in zip(queries, documents)]

# Tokenize the input texts
inputs = process_inputs(pairs)
scores = compute_logits(inputs)

print("scores: ", scores)

# Requires vllm>=0.8.5
import logging
from typing import Dict, Optional, List

import json
import logging

import torch

from transformers import AutoTokenizer, is_torch_npu_available
from vllm import LLM, SamplingParams
from vllm.distributed.parallel_state import destroy_model_parallel
import gc
import math
from vllm.inputs.data import TokensPrompt


        
def format_instruction(instruction, query, doc):
    text = [
        {"role": "system", "content": "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\"."},
        {"role": "user", "content": f"<Instruct>: {instruction}\n\n<Query>: {query}\n\n<Document>: {doc}"}
    ]
    return text

def process_inputs(pairs, instruction, max_length, suffix_tokens):
    messages = [format_instruction(instruction, query, doc) for query, doc in pairs]
    messages =  tokenizer.apply_chat_template(
        messages, tokenize=True, add_generation_prompt=False, enable_thinking=False
    )
    messages = [ele[:max_length] + suffix_tokens for ele in messages]
    messages = [TokensPrompt(prompt_token_ids=ele) for ele in messages]
    return messages

def compute_logits(model, messages, sampling_params, true_token, false_token):
    outputs = model.generate(messages, sampling_params, use_tqdm=False)
    scores = []
    for i in range(len(outputs)):
        final_logits = outputs[i].outputs[0].logprobs[-1]
        token_count = len(outputs[i].outputs[0].token_ids)
        if true_token not in final_logits:
            true_logit = -10
        else:
            true_logit = final_logits[true_token].logprob
        if false_token not in final_logits:
            false_logit = -10
        else:
            false_logit = final_logits[false_token].logprob
        true_score = math.exp(true_logit)
        false_score = math.exp(false_logit)
        score = true_score / (true_score + false_score)
        scores.append(score)
    return scores

number_of_gpu = torch.cuda.device_count()
tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-Reranker-4B')
model = LLM(model='Qwen/Qwen3-Reranker-4B', tensor_parallel_size=number_of_gpu, max_model_len=10000, enable_prefix_caching=True, gpu_memory_utilization=0.8)
tokenizer.padding_side = "left"
tokenizer.pad_token = tokenizer.eos_token
suffix = "<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
max_length=8192
suffix_tokens = tokenizer.encode(suffix, add_special_tokens=False)
true_token = tokenizer("yes", add_special_tokens=False).input_ids[0]
false_token = tokenizer("no", add_special_tokens=False).input_ids[0]
sampling_params = SamplingParams(temperature=0, 
    max_tokens=1,
    logprobs=20, 
    allowed_token_ids=[true_token, false_token],
)

        
task = 'Given a web search query, retrieve relevant passages that answer the query'
queries = ["What is the capital of China?",
    "Explain gravity",
]
documents = [
    "The capital of China is Beijing.",
    "Gravity is a force that attracts two bodies towards each other. It gives weight to physical objects and is responsible for the movement of planets around the sun.",
]

pairs = list(zip(queries, documents))
inputs = process_inputs(pairs, task, max_length-len(suffix_tokens), suffix_tokens)
scores = compute_logits(model, inputs, sampling_params, true_token, false_token)
print('scores', scores)

destroy_model_parallel()

@article{qwen3embedding,
  title={Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models},
  author={Zhang, Yanzhao and Li, Mingxin and Long, Dingkun and Zhang, Xin and Lin, Huan and Yang, Baosong and Xie, Pengjun and Yang, An and Liu, Dayiheng and Lin, Junyang and Huang, Fei and Zhou, Jingren},
  journal={arXiv preprint arXiv:2506.05176},
  year={2025}
}