AI 助理
备案控制台
开发者社区 大数据与机器学习 文章 正文

模型部署专题 | 01：基于Triton Server部署BERT模型

2023-06-23 1070
版权
版权声明：
本文内容由阿里云实名注册用户自发贡献，版权归原作者所有，阿里云开发者社区不拥有其著作权，亦不承担相应法律责任。具体规则请查看《 阿里云开发者社区用户服务协议》和 《阿里云开发者社区知识产权保护指引》。如果您发现本社区中有涉嫌抄袭的内容，填写 侵权投诉表单进行举报，一经查实，本社区将立刻删除涉嫌侵权内容。
本文涉及的产品
智能开放搜索 OpenSearch行业算法版，1GB 20LCU 1个月
推荐场景：
搭建高质量商品搜索服务
检索分析服务 Elasticsearch 版，2核4GB开发者规格 1个月
推荐场景：
数据可视化分析航班信息
实时计算 Flink 版，5000CU*H 3个月
推荐场景：
实时发现最热Github项目
简介： 本文简要介绍如何使用 Triton 部署 BERT模型

背景

本文简要介绍如何使用 Triton 部署 BERT模型，主要参考 NVIDIA/DeepLearningExamples

更多、更及时内容欢迎留意微信公众号： 小窗幽记机器学习

准备工作

下载数据

进入到/data/DeepLearningExamples-master/PyTorch/LanguageModeling/BERT/data/squad后，下载数据:

bash ./squad_download.sh

下载模型

wget --content-disposition https://api.ngc.nvidia.com/v2/models/nvidia/bert_large_pyt_amp_ckpt_squad_qa1_1/versions/1/zip -O bert_large_pyt_amp_ckpt_squad_qa1_1_1.zip

image.png

由于各个脚本使用的是bert_qa.pt，所以，对上述模型文件进行重命名。

构建容器

bash ./scripts/docker/build.sh

image.png

Processing triggers for libc-bin (2.27-3ubuntu1) ...
Removing intermediate container 89010b0a75b2
 ---> 562bcc14dbfa
Step 15/15 : COPY . .
 ---> 23bac3585a43
Successfully built 23bac3585a43
Successfully tagged bert:latest

模型部署

将 checkpoint 导出为 torchscript

在宿主机(不需要容器内部)下，进入DeepLearningExamples-master/PyTorch/LanguageModeling/BERT执行下述脚本将 checkpoint 转为 torchscript:

bash ./triton/export_model.sh

转换过程状态：

=============
== PyTorch ==
=============

NVIDIA Release 20.06 (build 13419386)
PyTorch Version 1.6.0a0+9907a3e

Container image Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.

Copyright (c) 2014-2020 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU                      (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015      Google Inc.
Copyright (c) 2015      Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

deploying model bertQA-ts-script in format pytorch_libtorch
/opt/conda/lib/python3.6/site-packages/torch/jit/_recursive.py:160: UserWarning: 'bias' was found in ScriptModule constants,  but it is a non-constant parameter. Consider removing it.
  " but it is a non-constant {}. Consider removing it.".format(name, hint))

conversion correctness test results
-----------------------------------
maximal absolute error over dataset (L_inf):  0.0322265625

average L_inf error over output tensors:  0.02264404296875
variance of L_inf error over output tensors:  5.4970383644104004e-05
stddev of L_inf error over output tensors:  0.00741420148391612

time of error check of native model:  0.8040032386779785 seconds
time of error check of ts model:  1.7353665828704834 seconds

done

模型格式转换后，待部署的Triton模型将存于BERT/results/triton_models。

image.png

./triton/export_model.sh中EXPORT_FORMAT值为ts-script表示转为torchscript格式。如果想要以ONNX格式部署，则可以将./triton/export_model.sh中的EXPORT_FORMAT值设置为onnx。此外，还要注意相应改动triton_model_name，比如改为bertQA-onnx，以对新转换的模型进行合适命名。

image.png

启动 Triton server

可以通过执行以下命令来启动Triton server:

docker run --rm --gpus device=0 --ipc=host --network=host -p 8000:8000 -p 8001:8001 -p 8002:8002 -v $PWD/results/triton_models:/models nvcr.io/nvidia/tritonserver:20.06-v1-py3 trtserver --model-store=/models --log-verbose=1

由于上述镜像nvcr.io/nvidia/tritonserver:20.06-v1-py3本地尚未拉取，所以执行上述命令后，会优先拉取该镜像。

另外，注意这里指定的模型位置是--model-store=/models映射的是./results/triton_models，且该目录下有2个模型，所以服务启动的时候会将2个模型都加载：

image.png

服务启动后，可以看下显存的占用情况：

image.png

启动自定义的Triton client

./triton/client.py为自定义的client代码。

Step1: 启动一个 client 容器

docker run -it --rm --ipc=host --network=host -v $PWD/vocab:/workspace/bert/vocab bert:latest

image.png

PS:
启动客户端无需指定GPU，且上述的启动方式，当在终端直接退出该容器后，该容器自动销毁。

如此便启动了一个容器，并进入容器当中。

Step2: 启动 client
进入到 client 代码目录:cd /workspace/bert/triton/，再运行如下代码，对 bertQA-ts-script 版模型进行请求：

python client.py --do_lower_case --version_2_with_negative --vocab_file=../vocab/vocab --triton-model-name=bertQA-ts-script

image.png

此时，client 端将向已在运行的 Triton server 发送一个请求，Triton server 接收请求并处理后，将请求返回。如果想输入自定义的文本段落和问题，则只需在运行client.py脚本时搭配--question和--context参数并传入对应的内容。此外，可以通过--triton-model-name指定特定的模型。这里服务端加载了2个模型，所以client也可以对 onnx 版模型进行请求：

python client.py --do_lower_case --version_2_with_negative --vocab_file=../vocab/vocab --triton-model-name=bertQA-onnx

image.png

模型部署后的评估：Squad1.1

部署并评估模型，可以在宿主机下执行以下命令

bash ./triton/evaluate.sh

PS:
在部署和评测之前，先将之前启动的 Triton server 关闭，否则端口被冲突。

服务启动和评测运行状态如下:

=============
== PyTorch ==
=============

NVIDIA Release 20.06 (build 13419386)
PyTorch Version 1.6.0a0+9907a3e

Container image Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.

Copyright (c) 2014-2020 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU                      (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015      Google Inc.
Copyright (c) 2015      Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

deploying model bert_large_fp32 in format pytorch_libtorch
/opt/conda/lib/python3.6/site-packages/torch/jit/_recursive.py:160: UserWarning: 'bias' was found in ScriptModule constants,  but it is a non-constant parameter. Consider removing it.
  " but it is a non-constant {}. Consider removing it.".format(name, hint))

conversion correctness test results
-----------------------------------
maximal absolute error over dataset (L_inf):  1.4185905456542969e-05

average L_inf error over output tensors:  1.0482966899871826e-05
variance of L_inf error over output tensors:  8.773056355456296e-12
stddev of L_inf error over output tensors:  2.961934562993635e-06

time of error check of native model:  1.596167802810669 seconds
time of error check of ts model:  2.414717435836792 seconds

done
Starting server...
Waiting for TRITON Server to be ready at http://localhost:8000...
000
.......TRITON Server is ready!

=============
== PyTorch ==
=============

NVIDIA Release 20.06 (build 13419386)
PyTorch Version 1.6.0a0+9907a3e

Container image Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.

Copyright (c) 2014-2020 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU                      (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015      Google Inc.
Copyright (c) 2015      Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

Sending Requests: 100%|███████████████████████████████████████████████████████████████████████████| 10833/10833 [04:20<00:00, 27.84sentences/s-----------------------------█████████████████████████████████████████████████████████████████████▉| 10832/10833 [14:29<00:00, 12.28sentences/s]
Individual Time Runs
Total Time: 869886.3623142242 ms
-----------------------------
-----------------------------
Total Inference Time = 432310.23 forSentences processed = 10833
Throughput Average (sentences/sec) = 12.45
Throughput Average (batches/sec) = 1.56
-----------------------------
-----------------------------
Summary Statistics
Batch size = 8
Sequence Length = 384
Latency Confidence Level 95 (ms) = 594040.61627388
Latency Confidence Level 99 (ms)  = 615392.275094986
Latency Confidence Level 100 (ms)  = 619993.6480522156
Latency Average (ms)  = 319048.1366518239
-----------------------------
Sending Requests: 100%|███████████████████████████████████████████████████████████████████████████| 10833/10833 [15:16<00:00, 11.82sentences/s]
Processed Requests: 100%|█████████████████████████████████████████████████████████████████████████| 10833/10833 [15:16<00:00, 11.82sentences/s]

=============
== PyTorch ==
=============

NVIDIA Release 20.06 (build 13419386)
PyTorch Version 1.6.0a0+9907a3e

Container image Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.

Copyright (c) 2014-2020 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU                      (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015      Google Inc.
Copyright (c) 2015      Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

trt_server_cont
tritonnet

需要注意的是，默认下以torchscript格式部署服务，并以Squad1.1数据集进行评测。如果想对onnx格式模型进行评测，将/triton/evaluate.sh中的EXPORT_FORMAT值从ts-script改为onnx。

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

deploying model bert_large_fp32 in format onnxruntime_onnx
/opt/conda/lib/python3.6/site-packages/torch/onnx/utils.py:955: UserWarning: No names were found for specified dynamic axes of provided input.Automatically generated names will be applied to each dynamic axes of input input__0
  'Automatically generated names will be applied to each dynamic axes of input {}'.format(key))
/opt/conda/lib/python3.6/site-packages/torch/onnx/utils.py:955: UserWarning: No names were found for specified dynamic axes of provided input.Automatically generated names will be applied to each dynamic axes of input input__1
  'Automatically generated names will be applied to each dynamic axes of input {}'.format(key))
/opt/conda/lib/python3.6/site-packages/torch/onnx/utils.py:955: UserWarning: No names were found for specified dynamic axes of provided input.Automatically generated names will be applied to each dynamic axes of input input__2
  'Automatically generated names will be applied to each dynamic axes of input {}'.format(key))
/opt/conda/lib/python3.6/site-packages/torch/onnx/utils.py:955: UserWarning: No names were found for specified dynamic axes of provided input.Automatically generated names will be applied to each dynamic axes of input output__0
  'Automatically generated names will be applied to each dynamic axes of input {}'.format(key))
/opt/conda/lib/python3.6/site-packages/torch/onnx/utils.py:955: UserWarning: No names were found for specified dynamic axes of provided input.Automatically generated names will be applied to each dynamic axes of input output__1
  'Automatically generated names will be applied to each dynamic axes of input {}'.format(key))
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:604] Reading dangerously large protocol message.  If the message turns out to be larger than 2147483647 bytes, parsing will be halted for security reasons.  To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h.
[libprotobuf WARNING google/protobuf/io/coded_stream.cc:81] The total number of bytes read was 1336539136

conversion correctness test results
-----------------------------------
maximal absolute error over dataset (L_inf):  0.00022530555725097656

average L_inf error over output tensors:  0.0001377016305923462
variance of L_inf error over output tensors:  6.448256743378049e-09
stddev of L_inf error over output tensors:  8.030103824595327e-05

time of error check of native model:  1.2507586479187012 seconds
time of error check of onnx model:  76.80649089813232 seconds

done
Starting server...
Waiting for TRITON Server to be ready at http://localhost:8000...
000
.......TRITON Server is ready!

=============
== PyTorch ==
=============

NVIDIA Release 20.06 (build 13419386)
PyTorch Version 1.6.0a0+9907a3e

Container image Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.

Copyright (c) 2014-2020 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU                      (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015      Google Inc.
Copyright (c) 2015      Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

Sending Requests: 100%|███████████████████████████████████████████████████████████████████████████| 10833/10833 [04:40<00:00, 15.52sentences/s-----------------------------█████████████████████████████████████████████████████████████████████▉| 10832/10833 [14:23<00:00, 12.42sentences/s]
Individual Time Runs
Total Time: 863938.3265972137 ms
-----------------------------
-----------------------------
Total Inference Time = 418017.89 forSentences processed = 10833
Throughput Average (sentences/sec) = 12.54
Throughput Average (batches/sec) = 1.57
-----------------------------
-----------------------------
Summary Statistics
Batch size = 8
Sequence Length = 384
Latency Confidence Level 95 (ms) = 568533.2419872284
Latency Confidence Level 99 (ms)  = 591532.5634479523
Latency Confidence Level 100 (ms)  = 595446.0487365723
Latency Average (ms)  = 308500.2912194087
-----------------------------
Sending Requests: 100%|███████████████████████████████████████████████████████████████████████████| 10833/10833 [15:10<00:00, 11.90sentences/s]
Processed Requests: 100%|█████████████████████████████████████████████████████████████████████████| 10833/10833 [15:10<00:00, 11.90sentences/s]

=============
== PyTorch ==
=============

NVIDIA Release 20.06 (build 13419386)
PyTorch Version 1.6.0a0+9907a3e

Container image Copyright (c) 2020, NVIDIA CORPORATION.  All rights reserved.

Copyright (c) 2014-2020 Facebook Inc.
Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
Copyright (c) 2011-2013 NYU                      (Clement Farabet)
Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
Copyright (c) 2015      Google Inc.
Copyright (c) 2015      Yangqing Jia
Copyright (c) 2013-2016 The Caffe contributors
All rights reserved.

Various files include modifications (c) NVIDIA CORPORATION.  All rights reserved.
NVIDIA modifications are covered by the license terms that apply to the underlying project or file.

NOTE: Legacy NVIDIA Driver detected.  Compatibility mode ENABLED.

NOTE: MOFED driver for multi-node communication was not detected.
      Multi-node communication performance may be reduced.

trt_server_cont
tritonnet

更多、更及时内容欢迎留意微信公众号： 小窗幽记机器学习

文章标签：
容器
机器学习/深度学习
算法框架/工具
异构计算
PyTorch
关键词：
bert模型
部署bert模型
小窗幽记机器学习
目录
相关文章
土木林森
|
1月前
|
自然语言处理 PyTorch 算法框架/工具
掌握从零到一的进阶攻略：让你轻松成为BERT微调高手——详解模型微调全流程，含实战代码与最佳实践秘籍，助你应对各类NLP挑战！
【10月更文挑战第1天】随着深度学习技术的进步，预训练模型已成为自然语言处理（NLP）领域的常见实践。这些模型通过大规模数据集训练获得通用语言表示，但需进一步微调以适应特定任务。本文通过简化流程和示例代码，介绍了如何选择预训练模型（如BERT），并利用Python库（如Transformers和PyTorch）进行微调。文章详细说明了数据准备、模型初始化、损失函数定义及训练循环等关键步骤，并提供了评估模型性能的方法。希望本文能帮助读者更好地理解和实现模型微调。
土木林森
69 2
掌握从零到一的进阶攻略：让你轻松成为BERT微调高手——详解模型微调全流程，含实战代码与最佳实践秘籍，助你应对各类NLP挑战！
aliyun7689123603-22772
|
1月前
|
机器学习/深度学习 自然语言处理 知识图谱
深入理解与探索：BERT模型的革命性影响
【10月更文挑战第3天】
aliyun7689123603-22772
54 1
sp_fyf_2024
|
29天前
|
机器学习/深度学习 自然语言处理 算法
[大语言模型-工程实践] 手把手教你-基于BERT模型提取商品标题关键词及优化改进
[大语言模型-工程实践] 手把手教你-基于BERT模型提取商品标题关键词及优化改进
sp_fyf_2024
85 0
楠竹11
|
2月前
|
搜索推荐 算法
模型小，还高效！港大最新推荐系统EasyRec：零样本文本推荐能力超越OpenAI、Bert
【9月更文挑战第21天】香港大学研究者开发了一种名为EasyRec的新推荐系统，利用语言模型的强大文本理解和生成能力，解决了传统推荐算法在零样本学习场景中的局限。EasyRec通过文本-行为对齐框架，结合对比学习和协同语言模型调优，提升了推荐准确性。实验表明，EasyRec在多个真实世界数据集上的表现优于现有模型，但其性能依赖高质量文本数据且计算复杂度较高。论文详见：http://arxiv.org/abs/2408.08821
楠竹11
57 7
小言从不摸鱼
|
1月前
|
机器学习/深度学习 人工智能 自然语言处理
【AI大模型】BERT模型：揭秘LLM主要类别架构（上）
【AI大模型】BERT模型：揭秘LLM主要类别架构（上）
小言从不摸鱼
88 0
BetterBench
|
3月前
|
机器学习/深度学习 存储 自然语言处理
【NLP-新闻文本分类】3 Bert模型的对抗训练
详细介绍了使用BERT模型进行新闻文本分类的过程，包括数据集预处理、使用预处理数据训练BERT语料库、加载语料库和词典后用原始数据训练BERT模型，以及模型测试。
BetterBench
64 1
格格的阿里云
|
3月前
|
算法 异构计算
自研分布式训练框架EPL问题之帮助加速Bert Large模型的训练如何解决
自研分布式训练框架EPL问题之帮助加速Bert Large模型的训练如何解决
格格的阿里云
34 0
算法金
|
4月前
|
机器学习/深度学习 人工智能 自然语言处理
算法金 | 秒懂 AI - 深度学习五大模型：RNN、CNN、Transformer、BERT、GPT 简介
**RNN**，1986年提出，用于序列数据，如语言模型和语音识别，但原始模型有梯度消失问题。**LSTM**和**GRU**通过门控解决了此问题。 **CNN**，1989年引入，擅长图像处理，卷积层和池化层提取特征，经典应用包括图像分类和物体检测，如LeNet-5。 **Transformer**，2017年由Google推出，自注意力机制实现并行计算，优化了NLP效率，如机器翻译。 **BERT**，2018年Google的双向预训练模型，通过掩码语言模型改进上下文理解，适用于问答和文本分类。
算法金
157 9
BetterBench
|
3月前
|
数据采集 人工智能 数据挖掘
2021 第五届“达观杯” 基于大规模预训练模型的风险事件标签识别】3 Bert和Nezha方案
2021第五届“达观杯”基于大规模预训练模型的风险事件标签识别比赛中使用的NEZHA和Bert方案，包括预训练、微调、模型融合、TTA测试集数据增强以及总结和反思。
BetterBench
43 0
aliyun7689123603-22772
|
4月前
|
数据采集 自然语言处理 PyTorch
AIGC之BERT模型
7月更文挑战第5天
aliyun7689123603-22772
77 0

大数据与机器学习

热门文章

最新文章

  • 1
    odps是什么?
  • 2
    MaxCompute执行作业慢的原因排查
  • 3
    2017杭州云栖大会FAQ（持续更新中）
  • 4
    流计算StreamCompute
  • 5
    品《阿里巴巴大数据实践-大数据之路》一书(下)
  • 6
    FM算法介绍
  • 7
    Mars——基于张量的统一分布式计算框架
  • 8
    DII—算法服务利器
  • 9
    Flink: 实时规则引擎助力新零售发展
  • 10
    大规模深度学习优化技术在PAI平台中的应用及实践
  • 1
    如何利用 Puppeteer 的 Evaluate 函数操作网页数据
    5
  • 2
    小红书商品详情API接口获取步骤
    7
  • 3
    不可不知道的Spring 框架七大模块
    8
  • 4
    1688 商品详情数据接口（1688.item_get）
    7
  • 5
    LLM2CLIP：使用大语言模型提升CLIP的文本处理，提高长文本理解和跨语言能力
    11
  • 6
    使用Python实现智能食品价格预测的深度学习模型
    14
  • 7
    基于圆柱体镜子和光线跟踪实现镜反射观测全景观图的matlab模拟仿真
    16
  • 8
    AI 写歌词，会让歌词创作变得更容易吗？
    9
  • 9
    淘宝京东商品详情页接口
    14
  • 10
    WOODWARD TG‐13E and TG‐17E Actuators
    12

    • 相关课程

    更多
  • 基于ASK轻松部署企业级Stable Diffusion
  • 云原生AI套件：一键训练大模型及部署GPU共享推理服务

    • 相关电子书

    更多
  • PAI-Megatron-Patch：灵骏集群训练 LLMs
  • MLeap + Combust.ML Deploy Your
  • 阿里云 Kubernetes+Kubeflow – 加速深度学习实验的利器

    • 相关实验场景

    更多
  • 使用PAI+LLaMA Factory微调Qwen2-VL模型，搭建文旅领域知识问答机器人
  • 函数计算一键部署AI大语言模型并会话
  • 【文生图】一键部署Stable Diffusion基于函数计算
  • 在云上部署ChatGLM2-6B大模型（GPU版）
  • 【自由换模型】基于函数计算一键部署 Stable Diffusion
  • 使用PAI-快速开始，低代码实现大语言模型微调和部署
    • 下一篇
    阿里云OSS设置跨域访问