transformers -U 1.1.2 Conda 安装 conda install conda-forge::transformers 1.1.3 从源码安装 pip install git+https://github.com/huggingface/transformers 我们建议您使用 Python3.8 及以上版本和 Pytorch 2.0 及以上版本。 3 Qwen 1.2 快速开始 仓库。以下我们将演示如何 使用 llama.cpp 运行 Qwen。 1.4.1 准备 这个示例适用于 Linux 或 MacOS 系统。第一步操作是：“克隆仓库并进入该目录： git clone https://github.com/ggerganov/llama.cpp cd llama.cpp 然后运行 make 命令： make 然后你就能使用 llama.cpp 运行 GGUF 文件。 cpp 为我们提供了评估 GGUF 模型 PPL 性能的方法。为了实现这一点，你需要准备一个数据集，比如 “wiki 测试”。这里我们展示了一个运行测试的例子。 第一步，下载数据集： wget https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-raw-v1.zip? �→ref=salesforce-research

词语矢量作为各种深度学习模型的输入值 • 示例深度学习架构： dual RNN ( dual LSTM) • 利用用户反馈数据来补充训练样本 正在进行的探索 17 聊天机器人(chatbot) • 聊天机器人是一种聊天代理，它通过电脑程序设计与人类通过音频或文本进行 智力对话。 --维基百科 • 未来，聊天应用将被看作是新的浏览器，而机器人程序将成为新的网站。这就 是互联网的新开始。--Ted Livingston

Vijayvargeeya, Muhyun Kim, dennismalmgren, adursun, Anirudh Dagar, liqingnz, 3 http://learnpython.org/ 4 https://discuss.d2l.ai/ 6 目录 Pedro Larroy, lgov, ati‐ozgur, Jun Wu, Matthias Blume, Lin Yuan, geogunow 5 https://discuss.d2l.ai/ 目录 7 练习 1. 在本书discuss.d2l.ai6的论坛上注册帐户。 2. 在计算机上安装Python。 3. 沿着本节底部的链接进入论坛，在那里可以寻求帮助、讨论这本书，并通过与作者和社区接触来找到问 题的答案。 Discussions7 6 https://discuss.d2l.ai/ 7 https://discuss 接下来，初始化终端Shell，以便我们可以直接运行conda。 ~/miniconda3/bin/conda init 现在关闭并重新打开当前的shell。并使用下面的命令创建一个新的环境： 8 https://conda.io/en/latest/miniconda.html 9 conda create --name d2l python=3.9 -y 现在激活 d2l 环境： conda

资 源 ❑ 提交错误或者修改等反馈意见，请在 Github Issues 页面提交： https://github.com/dragen1860/Deep-Learning-with-PyTorch-book/issues ❑ 本书主页，以及源代码，电子书下载，正式版也会在此同步更新： https://github.com/dragen1860/Deep-Learning-with-PyTorch-book 深度学习—深入理解人工智能算法设计》： https://item.jd.com/12954866.html ❑ 联系邮箱(一般问题建议 Github issues 交流)：liangqu.long AT gmail.com ❑ 配套视频课程(收费，提供答疑等全服务，比较适合初学者)： 深度学习与 TensorFlow 入门实战 深度学习与 PyTorch 入门实战 https://study.163 share=2&shareId=48000000184 7407&courseId=1209092816&_trace_c _p_k2_=9e74eb6f891d47cfaa6f00b5cb 5f617c https://study.163.com/course/courseMain.h tm?share=2&shareId=480000001847407& courseId=1208894818&_trace_c_p_k2_=8

Problematic Files/Input Accuracy Modified from https://upload.wikimedia.org/wikipedia/commons/d/dc/UnderwoodKeyboard_%28transparent%29.png https://upload.wikimedia.org/wikipedia/commons/1/18/1328102022_Document 02022_Document.png May be re-distributed in accordance with the terms of the CC-SA 4.0 license https://creativecommons.org/licenses/by-sa/4.0/deed.en AAPL FB 700 GOOG TXT BIDU ? ? ? ? © 2018 Bloomberg from https://commons.wikimedia.org/wiki/Category:Machine_learning_algorithms#/media/File:Moving_From_unknown_to_known_feature_spaces_based_on_TS-ELM_with_random_kernels_and_connections.tif https://commons

深度学习：GAN 主讲人：龙良曲 https://blog.openai.com/generative-models/ Our Goal: ?(?) https://www.mathworks.com/help/stats/simulate-data-from-a-gaussian-mixture- model.html What does ? ? looks like? http://www Discriminator https://towardsdatascience.com/generative-adversarial-networks-explained- 34472718707a How to train? https://lilianweng.github.io/lil-log/2017/08/20/from-GAN-to-WGAN.html Done! https://medium realistic samples https://drive.google.com/drive/folders/1lWC6XEPD0LT5KUnPXeve_kWeY-FxH002 Having Fun ▪ https://reiinakano.github.io/gan-playground/ ▪ https://affinelayer.com/pixsrv/ ▪ https://www.youtube

PAI平台的优势 1. 机器学习PAI: https://help.aliyun.com/product/30347.html 2. 阿里灵杰:https://www.zhihu.com/org/a-li-ling-jie 3. EasyRec: https://github.com/alibaba/EasyRec 4. 推荐解决方案: https://help.aliyun.com/document_detail/161927 com/document_detail/161927.html 5. EasyCV:https://github.com/alibaba/EasyCV 6. EasyNLP: https://github.com/alibaba/EasyNLP 7. AliGraph: https://github.com/alibaba/graph-learn 8. DSW: https://help.aliyun.com/document_detail/194831 com/document_detail/194831.html 9. DLC: https://help.aliyun.com/document_detail/165124.html 10. EAS: https://help.aliyun.com/document_detail/110980.html 11. Blade: https://help.aliyun.com/document_detail/205128

主讲：龙良曲 Outline Supervised Learning https://towardsdatascience.com/supervised-vs-unsupervised-learning-14f68e32ea8d Massive Unlabeled data Unsupervised Learning https://medium.com/intuitionmachine/pre to process ▪ Visualization: https://projector.tensorflow.org/ ▪ Taking advantages of unsupervised data ▪ Compression, denoising, super-resolution … Auto-Encoders https://towardsdatascience.com/ap com/applied-deep-learning-part-3-autoencoders- 1c083af4d798 https://towardsdatascience.com/a-wizards-guide-to-adversarial-autoencoders-part-1- autoencoder-d9a5f8795af4 How to Train? PCA V.S. Auto-Encoders

���� TensorFlow �����20181219� https://github.com/tensorflow/tensorflow/ TensorFlow �����20190304� https://github.com/tensorflow/tensorflow/ TensorFlow ���� https://github.com/tensorflow/tensorflow/tags ow/tags TensorFlow ���� https://github.com/tensorflow/tensorflow/releases TensorFlow ���� https://github.com/tensorflow/tensorflow/releases TensorFlow ���� https://github.com/tensorflow/tensorflow/releases/tag/v1 ow/releases/tag/v1.0.0 TensorFlow ������ https://timqian.com/star-history/ TensorFlow ������ https://timqian.com/star-history/ TensorFlow ������ https://timqian.com/star-history/ TensorFlow ��-TFX

ca/~vincentp/ift3395/lectures/backprop_old.pdf Multi-Output Perceptron ▪ Extend to cope with multi categories https://youtu.be/aygSMgK3BEM Perceptrons’ Limitation: 1969 http://science.sciencemag.org/content/165/3895/780 umontreal.ca/~vincentp/ift3395/lectures/backprop_old.pdf 1986 https://web.stanford.edu/class/psych209a/ReadingsByDate/02_06/PDPVolIChapter8.pdf https://www.cs.cmu.edu/~epxing/Class/10715/reading/Kornick_et_al prop_old.pdf On DSP http://www.iro.umontreal.ca/~vincentp/ift3395/lectures/backprop_old.pdf ▪ https://youtu.be/FwFduRA_L6Q ▪ At some point in the late 1990s, one of these systems was reading 10 to