关于Ragflow、Dify、FastGPT不支持ollama重排模型的解决方法：

1、截止2025年6月11日，ollama暂不支持重排模型。经测试Ragflow 0.19和Dify不支持ollama的重排模型，添加所有ollama的重排模型时均会提示错误。FastGPT虽然可以添加，但是重排无效。

2、如需要使用重排模型，可以选择api或者本地用vllm部署重排模型。经过实测，在低参数量下，bge-reranker-v2-m3和bce-reranker-base_v1的重排序效果优于Qwen3-Reranker-0.6B。因此硬件条件满足情况下建议使用Qwen3-Reranker-4B-F16、Qwen3-Reranker-8B-F16或原版来部署重排模型。

vllm直接部署Qwen3-Reranker-4B的临时解决方法：https://www.modelscope.cn/models/dengcao/Qwen3-Reranker-4B

为彻底解决这个问题，期待ollama尽快推出支持重排模型的版本。

关于量化版本的说明：

q8_0：与浮点数16几乎无法区分。资源使用率高，速度慢。不建议大多数用户使用。

q6_k：将Q8_K用于所有张量。

q5_k_m：将 Q6_K 用于一半的 attention.wv 和 feed_forward.w2 张量，否则Q5_K。

q5_0： 原始量化方法，5位。精度更高，资源使用率更高，推理速度更慢。

q4_k_m：将 Q6_K 用于一半的 attention.wv 和 feed_forward.w2 张量，否则Q4_K

q4_0：原始量化方法，4 位。

q3_k_m：将 Q4_K 用于 attention.wv、attention.wo 和 feed_forward.w2 张量，否则Q3_K

q2_k：将 Q4_K 用于 attention.vw 和 feed_forward.w2 张量，Q2_K用于其他张量。

根据经验，建议使用 Q5_K_M，因为它保留了模型的大部分性能。或者，如果要节省一些内存，可以使用 Q4_K_M。

license: apache-2.0 base_model: - Qwen/Qwen3-4B-Base

library_name: transformers

Qwen3-Reranker-4B

Highlights

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

Exceptional Versatility: The embedding model has achieved state-of-the-art performance across a wide range of downstream application evaluations. The 8B size embedding model ranks No.1 in the MTEB multilingual leaderboard (as of June 5, 2025, score 70.58), while the reranking model excels in various text retrieval scenarios.

Comprehensive Flexibility: The Qwen3 Embedding series offers a full spectrum of sizes (from 0.6B to 8B) for both embedding and reranking models, catering to diverse use cases that prioritize efficiency and effectiveness. Developers can seamlessly combine these two modules. Additionally, the embedding model allows for flexible vector definitions across all dimensions, and both embedding and reranking models support user-defined instructions to enhance performance for specific tasks, languages, or scenarios.

Multilingual Capability: The Qwen3 Embedding series offer support for over 100 languages, thanks to the multilingual capabilites of Qwen3 models. This includes various programming languages, and provides robust multilingual, cross-lingual, and code retrieval capabilities.

Qwen3-Reranker-4B has the following features:

• Model Type: Text Reranking
• Supported Languages: 100+ Languages
• Number of Paramaters: 4B
• Context Length: 32k

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our blog, GitHub.

Qwen3 Embedding Series Model list

Note: - MRL Support indicates whether the embedding model supports custom dimensions for the final embedding. - Instruction Aware notes whether the embedding or reranking model supports customizing the input instruction according to different tasks. - Our evaluation indicates that, for most downstream tasks, using instructions (instruct) typically yields an improvement of 1% to 5% compared to not using them. Therefore, we recommend that developers create tailored instructions specific to their tasks and scenarios. In multilingual contexts, we also advise users to write their instructions in English, as most instructions utilized during the model training process were originally written in English.

Usage

With Transformers versions earlier than 4.51.0, you may encounter the following error:

KeyError: 'qwen3'

Transformers Usage

# 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)

vLLM Usage

# 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()

📌 Tip: We recommend that developers customize the instruct according to their specific scenarios, tasks, and languages. Our tests have shown that in most retrieval scenarios, not using an instruct on the query side can lead to a drop in retrieval performance by approximately 1% to 5%.

Evaluation

Note:
- Evaluation results for reranking models. We use the retrieval subsets of MTEB(eng, v2), MTEB(cmn, v1), MMTEB and MTEB (Code), which are MTEB-R, CMTEB-R, MMTEB-R and MTEB-Code. - All scores are our runs based on the top-100 candidates retrieved by dense embedding model Qwen3-Embedding-0.6B.

Citation

If you find our work helpful, feel free to give us a cite.

@misc{qwen3-embedding,
    title  = {Qwen3-Embedding},
    url    = {https://qwenlm.github.io/blog/qwen3/},
    author = {Qwen Team},
    month  = {May},
    year   = {2025}
}