【错误记录】CrossEncoder 从 Hugging Face 模型库中下载模型报错 ( ConnectionError: (ProtocolError(‘Connection aborted )

一、报错信息二、问题分析1、查看本地模型缓存2、使用 Python 代码测试网络3、终极解决方案 - 手动下载模型三、解决方案1、网络问题 - 清除代理2、问题解决后成功执行

韩曙亮

1708人浏览 · 2025-03-10 10:29:09

韩曙亮 · 2025-03-10 10:29:09 发布

文章目录

一、报错信息
二、问题分析
三、解决方案
- 1、网络问题 - 清除代理
- 2、问题解决后成功执行

一、报错信息

运行 https://www.sbert.net/docs/quickstart.html 文档中的代码 ,

from sentence_transformers.cross_encoder import CrossEncoder

# 1. Load a pretrained CrossEncoder model
model = CrossEncoder("cross-encoder/stsb-distilroberta-base")

# We want to compute the similarity between the query sentence...
query = "A man is eating pasta."

# ... and all sentences in the corpus
corpus = [
    "A man is eating food.",
    "A man is eating a piece of bread.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
    "A woman is playing violin.",
    "Two men pushed carts through the woods.",
    "A man is riding a white horse on an enclosed ground.",
    "A monkey is playing drums.",
    "A cheetah is running behind its prey.",
]

# 2. We rank all sentences in the corpus for the query
ranks = model.rank(query, corpus)

# Print the scores
print("Query: ", query)
for rank in ranks:
    print(f"{rank['score']:.2f}\t{corpus[rank['corpus_id']]}")
"""
Query:  A man is eating pasta.
0.67    A man is eating food.
0.34    A man is eating a piece of bread.
0.08    A man is riding a horse.
0.07    A man is riding a white horse on an enclosed ground.
0.01    The girl is carrying a baby.
0.01    Two men pushed carts through the woods.
0.01    A monkey is playing drums.
0.01    A woman is playing violin.
0.01    A cheetah is running behind its prey.
"""

# 3. Alternatively, you can also manually compute the score between two sentences
import numpy as np

sentence_combinations = [[query, sentence] for sentence in corpus]
scores = model.predict(sentence_combinations)

# Sort the scores in decreasing order to get the corpus indices
ranked_indices = np.argsort(scores)[::-1]
print("Scores:", scores)
print("Indices:", ranked_indices)
"""
Scores: [0.6732372, 0.34102544, 0.00542465, 0.07569341, 0.00525378, 0.00536814, 0.06676237, 0.00534825, 0.00516717]
Indices: [0 1 3 6 2 5 7 4 8]
"""

为其配置 Hugging Face 的国内镜像 ,

import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"  # 设置Hugging Face模型的下载镜像地址，核心配置用于加速模型下载

最终运行还是报错 :

D:\001_Develop\022_Python\Python39\python.exe D:/002_Project/011_Python/OpenAI/cross_encoder.py
Traceback (most recent call last):
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
    response = self._make_request(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connectionpool.py", line 534, in _make_request
    response = conn.getresponse()
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connection.py", line 516, in getresponse
    httplib_response = super().getresponse()
  File "D:\001_Develop\022_Python\Python39\lib\http\client.py", line 1371, in getresponse
    response.begin()
  File "D:\001_Develop\022_Python\Python39\lib\http\client.py", line 319, in begin
    version, status, reason = self._read_status()
  File "D:\001_Develop\022_Python\Python39\lib\http\client.py", line 288, in _read_status
    raise RemoteDisconnected("Remote end closed connection without"
http.client.RemoteDisconnected: Remote end closed connection without response

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\requests\adapters.py", line 667, in send
    resp = conn.urlopen(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connectionpool.py", line 841, in urlopen
    retries = retries.increment(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\util\retry.py", line 474, in increment
    raise reraise(type(error), error, _stacktrace)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\util\util.py", line 38, in reraise
    raise value.with_traceback(tb)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
    response = self._make_request(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connectionpool.py", line 534, in _make_request
    response = conn.getresponse()
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\urllib3\connection.py", line 516, in getresponse
    httplib_response = super().getresponse()
  File "D:\001_Develop\022_Python\Python39\lib\http\client.py", line 1371, in getresponse
    response.begin()
  File "D:\001_Develop\022_Python\Python39\lib\http\client.py", line 319, in begin
    version, status, reason = self._read_status()
  File "D:\001_Develop\022_Python\Python39\lib\http\client.py", line 288, in _read_status
    raise RemoteDisconnected("Remote end closed connection without"
urllib3.exceptions.ProtocolError: ('Connection aborted.', RemoteDisconnected('Remote end closed connection without response'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "D:\002_Project\011_Python\OpenAI\cross_encoder.py", line 7, in <module>
    model = CrossEncoder("cross-encoder/stsb-distilroberta-base")
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\sentence_transformers\cross_encoder\CrossEncoder.py", line 82, in __init__
    self.config = AutoConfig.from_pretrained(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\transformers\models\auto\configuration_auto.py", line 1075, in from_pretrained
    config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\transformers\configuration_utils.py", line 594, in get_config_dict
    config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\transformers\configuration_utils.py", line 653, in _get_config_dict
    resolved_config_file = cached_file(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\transformers\utils\hub.py", line 342, in cached_file
    resolved_file = hf_hub_download(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\file_download.py", line 862, in hf_hub_download
    return _hf_hub_download_to_cache_dir(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\file_download.py", line 1011, in _hf_hub_download_to_cache_dir
    _download_to_tmp_and_move(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\file_download.py", line 1547, in _download_to_tmp_and_move
    http_get(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\file_download.py", line 371, in http_get
    r = _request_wrapper(
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\file_download.py", line 303, in _request_wrapper
    response = get_session().request(method=method, url=url, **params)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\requests\sessions.py", line 589, in request
    resp = self.send(prep, **send_kwargs)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\requests\sessions.py", line 703, in send
    r = adapter.send(request, **kwargs)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\huggingface_hub\utils\_http.py", line 96, in send
    return super().send(request, *args, **kwargs)
  File "D:\001_Develop\022_Python\Python39\lib\site-packages\requests\adapters.py", line 682, in send
    raise ConnectionError(err, request=request)
requests.exceptions.ConnectionError: (ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response')), '(Request ID: 3295b6db-1ef1-4e00-943d-eefe67e0a29d)')

Process finished with exit code 1

核心报错信息如下 :

requests.exceptions.ConnectionError: (ProtocolError('Connection aborted.', RemoteDisconnected('Remote end closed connection without response')), '(Request ID: 3295b6db-1ef1-4e00-943d-eefe67e0a29d)')

requests.exceptions.ConnectionError: (
ProtocolError(‘Connection aborted.’, RemoteDisconnected(
‘Remote end closed connection without response’)), ‘(
Request ID: 3295b6db-1ef1-4e00-943d-eefe67e0a29d)’)

在这里插入图片描述

二、问题分析

1、查看本地模型缓存

执行

import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"  # 设置Hugging Face模型的下载镜像地址，核心配置用于加速模型下载

from sentence_transformers.cross_encoder import CrossEncoder

# 1. Load a pretrained CrossEncoder model
model = CrossEncoder("cross-encoder/stsb-distilroberta-base")

代码 , 下载 “cross-encoder/stsb-distilroberta-base” 模型 , 本地下载的模型目录是 C:\Users\octop.cache\huggingface\hub\models–cross-encoder–stsb-distilroberta-base 地址 ,

在这里插入图片描述

可能是本地缓存被破坏 , 可以手动删除损坏的缓存文件 , 或者使用如下代码删除缓存文件 ;

from huggingface_hub import snapshot_download
# 删除旧缓存并重新下载
model_path = snapshot_download(
    "cross-encoder/stsb-distilroberta-base",
    force_download=True,  # 强制重新下载
    resume_download=False # 禁用断点续传
)

2、使用 Python 代码测试网络

在代码中检查网络连通性 , 使用 request 库中的 requests.get 函数 , 测试网络连通性 ;

在 PyCharm 中执行下面的代码 :

# 测试是否可访问Hugging Face服务器
import requests
try:
    response = requests.get("https://huggingface.co/", timeout=10)
    print("网络连通正常" if response.status_code == 200 else "服务器响应异常")
except Exception as e:
    print(f"网络连接失败: {str(e)}")

输出结果如下 :

网络连接失败: ('Connection aborted.', ConnectionResetError(10054, '远程主机强迫关闭了一个现有的连接。', None, 10054, None))

在这里插入图片描述

遇到网络问题 , 可以进行如下尝试 :

切换网络 : 换个 WIFI 连接 , 暂时使用手机热点连接 ;
设置代理 : 检查防火墙 / 代理设置 ;

3、终极解决方案 - 手动下载模型

参考【错误记录】本地部署大模型从 Hugging Face 的模型库下载模型报错 ( OSError: We couldn‘t connect to ‘https://huggingface.co‘ ) 三、解决方案 1、解决方案 1 - 手动下载模型解决方案 , 从 Hugging Face 模型库 https://huggingface.co 中 , 手动下载模型文件 , 需要下载的模型文件参考 C:\Users\octop.cache\huggingface\hub\models–cross-encoder–stsb-distilroberta-base\snapshots\9a05a97ddb424fc9aea3d768d0e2dab0a1276421 目录 :

在这里插入图片描述
这是成功下载后的模型文件 ;

如果不知道下载哪个模型文件 , 那就全部下载 , 涉及到目录需要手动创建 , 目录中的文件需要下载下来手动移动到你创建的文件中 ;

三、解决方案

1、网络问题 - 清除代理

遇到网络问题 , 可以进行如下尝试 :

切换网络 : 换个 WIFI 连接 , 暂时使用手机热点连接 ;
设置代理 : 检查防火墙 / 代理设置 ;

之前使用了魔法工具 , 没有断开连接 , 直接关机 ;

再次开启魔法工具 , 清除代理 ;

在这里插入图片描述

然后再次执行如下代码 ,

# 测试是否可访问Hugging Face服务器
import requests
try:
    response = requests.get("https://huggingface.co/", timeout=10)
    print("网络连通正常" if response.status_code == 200 else "服务器响应异常")
except Exception as e:
    print(f"网络连接失败: {str(e)}")

执行结果 :

网络连接失败: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: / (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000001929BB106A0>, 'Connection to huggingface.co timed out. (connect timeout=10)'))

网络连接失败: HTTPSConnectionPool(host=‘huggingface.co’, port=443):
Max retries exceeded with url: /
(Caused by ConnectTimeoutError
(<urllib3.connection.HTTPSConnection object at 0x000001929BB106A0>,
‘Connection to huggingface.co timed out. (connect timeout=10)’))

将代码中的网址切换成镜像地址 https://hf-mirror.com , 再次执行下面的代码 :

# 测试是否可访问Hugging Face服务器
import requests
try:
    response = requests.get("https://hf-mirror.com", timeout=10)
    print("网络连通正常" if response.status_code == 200 else "服务器响应异常")
except Exception as e:
    print(f"网络连接失败: {str(e)}")

执行结果 :

网络连通正常

在这里插入图片描述

2、问题解决后成功执行

再次执行如下设置完镜像网站的代码 :

import os
os.environ["HF_ENDPOINT"] = "https://hf-mirror.com"  # 设置Hugging Face模型的下载镜像地址，核心配置用于加速模型下载

from sentence_transformers.cross_encoder import CrossEncoder

# 1. Load a pretrained CrossEncoder model
model = CrossEncoder("cross-encoder/stsb-distilroberta-base")

# We want to compute the similarity between the query sentence...
query = "A man is eating pasta."

# ... and all sentences in the corpus
corpus = [
    "A man is eating food.",
    "A man is eating a piece of bread.",
    "The girl is carrying a baby.",
    "A man is riding a horse.",
    "A woman is playing violin.",
    "Two men pushed carts through the woods.",
    "A man is riding a white horse on an enclosed ground.",
    "A monkey is playing drums.",
    "A cheetah is running behind its prey.",
]

# 2. We rank all sentences in the corpus for the query
ranks = model.rank(query, corpus)

# Print the scores
print("Query: ", query)
for rank in ranks:
    print(f"{rank['score']:.2f}\t{corpus[rank['corpus_id']]}")
"""
Query:  A man is eating pasta.
0.67    A man is eating food.
0.34    A man is eating a piece of bread.
0.08    A man is riding a horse.
0.07    A man is riding a white horse on an enclosed ground.
0.01    The girl is carrying a baby.
0.01    Two men pushed carts through the woods.
0.01    A monkey is playing drums.
0.01    A woman is playing violin.
0.01    A cheetah is running behind its prey.
"""

# 3. Alternatively, you can also manually compute the score between two sentences
import numpy as np

sentence_combinations = [[query, sentence] for sentence in corpus]
scores = model.predict(sentence_combinations)

# Sort the scores in decreasing order to get the corpus indices
ranked_indices = np.argsort(scores)[::-1]
print("Scores:", scores)
print("Indices:", ranked_indices)
"""
Scores: [0.6732372, 0.34102544, 0.00542465, 0.07569341, 0.00525378, 0.00536814, 0.06676237, 0.00534825, 0.00516717]
Indices: [0 1 3 6 2 5 7 4 8]
"""

执行结果如下 :

在这里插入图片描述

查看 C:\Users\octop.cache\huggingface\hub\models–cross-encoder–stsb-distilroberta-base 模型目录 , 就是下载后 314 MB 的模型 ;

在这里插入图片描述

火山引擎开发者社区

火山引擎开发者社区是火山引擎打造的AI技术生态平台，聚焦Agent与大模型开发，提供豆包系列模型（图像/视频/视觉）、智能分析与会话工具，并配套评测集、动手实验室及行业案例库。社区通过技术沙龙、挑战赛等活动促进开发者成长，新用户可领50万Tokens权益，助力构建智能应用。

更多推荐

OBS Studio音频分离：人声与背景音乐分离全攻略

你是否曾在直播或录屏时遇到这样的困境：想要单独调整人声音量却影响了背景音乐，或是后期剪辑时无法消除环境噪音？OBS Studio（Open Broadcaster Software Studio，开放广播软件工作室）作为免费开源的音视频录制与直播工具，提供了强大的音频处理框架，通过合理配置滤镜链与外部工具组合，可实现专业级别的人声与背景音乐分离。本文将系统讲解3种分离方案，从基础声道分离到AI驱动

火山引擎开发者社区

lmstudio-python：简化LLM操作的强大Python SDK

lmstudio-python 是一款功能强大的 Python SDK，旨在帮助开发者轻松地使用大型语言模型（LLM）进行文本生成、对话系统搭建以及其他相关应用。通过简单易用的API，lmstudio-python 能够让用户快速集成 LLM 功能，无论是进行基础文本补全还是复杂的对话系统设计。## 项目技术分析lmstudio-python SDK 以 Python 为基础，提供了一个同

火山引擎开发者社区

OBS Studio AI增强：智能场景识别与自动优化全攻略

你是否曾在直播切换场景时手忙脚乱？是否因复杂的参数配置而错失最佳直播时机？OBS Studio作为开源直播软件的佼佼者，虽提供强大的自定义功能，但传统手动操作已难以满足专业创作者对效率和质量的双重需求。本文将系统介绍如何通过AI技术增强OBS Studio的核心能力，重点实现智能场景识别与自动参数优化，让你的直播制作流程效率提升300%。读完本文你将获得：- 基于OpenCV的实时场景分析插