▲
0
0

report

Build an LLM from Scratch: Code a GPT in PyTorch [10/2026, ENG]

seeders: 3
leechers: 4
Download torrent
Added 5 days ago by unity321d in Other
Download Fast Safe Anonymous
movies, software, shows...

Files

Build an LLM from Scratch: Code a GPT in PyTorch [10/2026, ENG] (Size: 1.98 GB)
  1 - Welcome
  1. Course introduction.mp4 40.26 MB
  1. Course introduction_en-US.srt 5.7 KB
  2. Appendix A A PyTorch Primer.mp4 61.23 MB
  2. Appendix A A PyTorch Primer_en-US.srt 8.18 KB
  2 - Chapter 1 Understanding Large Language Models
  1. Chapter 1 quiz Understanding large language models.html 26.93 KB
  3. Intro & 1.1 What is a large language model.mp4 14.05 MB
  3. Intro & 1.1 What is a large language model_en-US.srt 1.56 KB
  4. 1.2 Applications of LLMs & 1.3 Stages of building and using LLMs.mp4 13.3 MB
  4. 1.2 Applications of LLMs & 1.3 Stages of building and using LLMs_en-US.srt 1.79 KB
  5. 1.4 Introducing the transformer architecture & 1.5 Utilizing large datasets.mp4 13.95 MB
  5. 1.4 Introducing the transformer architecture & 1.5 Utilizing large datasets_en-US.srt 1.8 KB
  6. 1.6 A closer look at the GPT architecture.mp4 14.8 MB
  6. 1.6 A closer look at the GPT architecture_en-US.srt 1.56 KB
  7. A counting language model & 1.7 Building a large language model.mp4 21.17 MB
  7. A counting language model & 1.7 Building a large language model_en-US.srt 2.89 KB
  ch01
  NOTICE.txt 558 B
  data
  scandal_in_bohemia.txt 45.41 KB
  gpt_download.py 5.83 KB
  gpt_weights.py 3.44 KB
  notebooks
  practice.ipynb 9.73 KB
  solution.ipynb 21.64 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  3 - Chapter 2 Working with Text Data
  10. 2.4 Adding special context tokens & 2.5 Byte pair encoding.mp4 14.83 MB
  10. 2.4 Adding special context tokens & 2.5 Byte pair encoding_en-US.srt 1.72 KB
  11. 2.6 Data sampling with a sliding window.mp4 13.01 MB
  11. 2.6 Data sampling with a sliding window_en-US.srt 1.33 KB
  12. 2.7 Creating token embeddings & 2.8 Encoding word positions.mp4 21.58 MB
  12. 2.7 Creating token embeddings & 2.8 Encoding word positions_en-US.srt 2.59 KB
  13. Extra (optional) Byte Pair Encoding from Scratch.mp4 35.09 MB
  13. Extra (optional) Byte Pair Encoding from Scratch_en-US.srt 4.4 KB
  14. Extra (optional) Comparing BPE Implementations.mp4 20.91 MB
  14. Extra (optional) Comparing BPE Implementations_en-US.srt 2.35 KB
  15. Extra (optional) Embedding Layers vs. Linear Layers.mp4 16.97 MB
  15. Extra (optional) Embedding Layers vs. Linear Layers_en-US.srt 1.93 KB
  16. Extra (optional) The Data Loader with Plain Numbers.mp4 14.3 MB
  16. Extra (optional) The Data Loader with Plain Numbers_en-US.srt 1.72 KB
  17. Extra (optional) SimpleTokenizerV3.mp4 12.92 MB
  17. Extra (optional) SimpleTokenizerV3_en-US.srt 1.38 KB
  2. Chapter 2 quiz Working with text data.html 26.37 KB
  8. Intro & 2.1 Understanding word embeddings.mp4 15.22 MB
  8. Intro & 2.1 Understanding word embeddings_en-US.srt 1.85 KB
  9. 2.2 Tokenizing text & 2.3 Converting tokens into token IDs.mp4 13.5 MB
  9. 2.2 Tokenizing text & 2.3 Converting tokens into token IDs_en-US.srt 1.49 KB
  ch02
  NOTICE.txt 558 B
  data
  scandal_in_bohemia.txt 45.41 KB
  gpt_download.py 5.83 KB
  gpt_weights.py 3.44 KB
  notebooks
  practice.ipynb 13.59 KB
  solution.ipynb 31.24 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  4 - Chapter 3 Coding Attention Mechanisms
  18. Intro & 3.1 The problem with modeling long sequences.mp4 16.49 MB
  18. Intro & 3.1 The problem with modeling long sequences_en-US.srt 1.99 KB
  19. 3.2 Capturing dependencies with attention & 3.3 Self-attention.mp4 22.57 MB
  19. 3.2 Capturing dependencies with attention & 3.3 Self-attention_en-US.srt 2.75 KB
  20. 3.4 Implementing self-attention with trainable weights.mp4 17.08 MB
  20. 3.4 Implementing self-attention with trainable weights_en-US.srt 1.96 KB
  21. 3.5 Hiding future words with causal attention.mp4 18.38 MB
  21. 3.5 Hiding future words with causal attention_en-US.srt 1.71 KB
  22. 3.6 Extending single-head attention to multi-head attention.mp4 15.64 MB
  22. 3.6 Extending single-head attention to multi-head attention_en-US.srt 2.23 KB
  23. Extra (optional) Nine Ways to Implement Multi-Head Attention.mp4 46.51 MB
  23. Extra (optional) Nine Ways to Implement Multi-Head Attention_en-US.srt 6.31 KB
  24. Extra (optional) Understanding PyTorch Buffers.mp4 28.51 MB
  24. Extra (optional) Understanding PyTorch Buffers_en-US.srt 3.7 KB
  3. Chapter 3 quiz Coding attention mechanisms.html 27.07 KB
  ch03
  NOTICE.txt 558 B
  gpt_download.py 5.83 KB
  gpt_weights.py 3.44 KB
  notebooks
  practice.ipynb 13.97 KB
  solution.ipynb 30.28 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  5 - Chapter 4 Implementing a GPT Model from Scratch
  25. Intro & 4.1 Coding an LLM architecture.mp4 21.81 MB
  25. Intro & 4.1 Coding an LLM architecture_en-US.srt 2.53 KB
  26. 4.2 Layer normalization & 4.3 Feed forward network with GELU.mp4 14.59 MB
  26. 4.2 Layer normalization & 4.3 Feed forward network with GELU_en-US.srt 1.87 KB
  27. 4.4 Shortcut connections & 4.5 The transformer block.mp4 11.27 MB
  27. 4.4 Shortcut connections & 4.5 The transformer block_en-US.srt 1.5 KB
  28. 4.6 Coding the GPT model.mp4 12.52 MB
  28. 4.6 Coding the GPT model_en-US.srt 1.22 KB
  29. 4.7 Generating text.mp4 14.05 MB
  29. 4.7 Generating text_en-US.srt 1.94 KB
  30. Extra (optional) FLOPs and Model FLOPs Utilization.mp4 8.54 MB
  30. Extra (optional) FLOPs and Model FLOPs Utilization_en-US.srt 2.66 KB
  31. Extra (optional) The KV Cache.mp4 28.86 MB
  31. Extra (optional) The KV Cache_en-US.srt 4.29 KB
  32. Extra (optional) Grouped-Query Attention (GQA).mp4 27.81 MB
  32. Extra (optional) Grouped-Query Attention (GQA)_en-US.srt 3.39 KB
  33. Extra (optional) Multi-Head Latent Attention (MLA).mp4 29.65 MB
  33. Extra (optional) Multi-Head Latent Attention (MLA)_en-US.srt 3.82 KB
  34. Extra (optional) Sliding Window Attention (SWA).mp4 25.51 MB
  34. Extra (optional) Sliding Window Attention (SWA)_en-US.srt 3.51 KB
  35. Extra (optional) Mixture of Experts (MoE).mp4 13.94 MB
  35. Extra (optional) Mixture of Experts (MoE)_en-US.srt 4.05 KB
  36. Extra (optional) Gated DeltaNet and Linear Attention.mp4 28.12 MB
  36. Extra (optional) Gated DeltaNet and Linear Attention_en-US.srt 3.59 KB
  37. Extra (optional) DeepSeek Sparse Attention (DSA).mp4 10.39 MB
  37. Extra (optional) DeepSeek Sparse Attention (DSA)_en-US.srt 3.23 KB
  38. Extra (optional) Cross-Layer KV Sharing.mp4 11.49 MB
  38. Extra (optional) Cross-Layer KV Sharing_en-US.srt 3.4 KB
  4. Chapter 4 quiz Implementing a GPT model from scratch.html 26.29 KB
  ch04
  NOTICE.txt 558 B
  gpt_download.py 5.83 KB
  gpt_weights.py 3.54 KB
  notebooks
  practice.ipynb 14.94 KB
  solution.ipynb 28.45 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  6 - Chapter 5 Pretraining on Unlabeled Data
  39. Intro.mp4 15.8 MB
  39. Intro_en-US.srt 1.56 KB
  40. 5.1 Evaluating generative text models.mp4 13.13 MB
  40. 5.1 Evaluating generative text models_en-US.srt 1.39 KB
  41. Inputs and targets & Cross-entropy and perplexity.mp4 8.16 MB
  41. Inputs and targets & Cross-entropy and perplexity_en-US.srt 2.25 KB
  42. Training and validation data.mp4 14.06 MB
  42. Training and validation data_en-US.srt 1.65 KB
  43. 5.2 Training an LLM & Loss curves and samples.mp4 20.22 MB
  43. 5.2 Training an LLM & Loss curves and samples_en-US.srt 2.5 KB
  44. 5.3 Decoding strategies to control randomness & Temperature scaling.mp4 12.39 MB
  44. 5.3 Decoding strategies to control randomness & Temperature scaling_en-US.srt 1.42 KB
  45. Top-k sampling & 5.4 Saving and loading model weights.mp4 19.34 MB
  45. Top-k sampling & 5.4 Saving and loading model weights_en-US.srt 1.83 KB
  46. 5.5 Loading pretrained weights from OpenAI & Loading weights into GPTModel.mp4 23.58 MB
  46. 5.5 Loading pretrained weights from OpenAI & Loading weights into GPTModel_en-US.srt 3.19 KB
  47. Extra (optional) Alternative Ways to Load GPT-2 Weights.mp4 46.2 MB
  47. Extra (optional) Alternative Ways to Load GPT-2 Weights_en-US.srt 5.79 KB
  48. Extra (optional) Pretraining GPT on Project Gutenberg.mp4 48.33 MB
  48. Extra (optional) Pretraining GPT on Project Gutenberg_en-US.srt 7.09 KB
  49. Extra (optional) Warmup, Cosine Decay and Gradient Clipping.mp4 31.73 MB
  49. Extra (optional) Warmup, Cosine Decay and Gradient Clipping_en-US.srt 4.97 KB
  5. Chapter 5 quiz Pretraining on unlabeled data.html 27.13 KB
  50. Extra (optional) Hyperparameter Search for Pretraining.mp4 24.45 MB
  50. Extra (optional) Hyperparameter Search for Pretraining_en-US.srt 3.14 KB
  51. Extra (optional) A Chat Interface for GPT-2.mp4 26.25 MB
  51. Extra (optional) A Chat Interface for GPT-2_en-US.srt 3.77 KB
  52. Extra (optional) From GPT to Llama 2, Llama 3 and Llama 3.2.mp4 97.56 MB
  52. Extra (optional) From GPT to Llama 2, Llama 3 and Llama 3.2_en-US.srt 12.56 KB
  53. Extra (optional) Memory-Efficient Weight Loading.mp4 37.93 MB
  53. Extra (optional) Memory-Efficient Weight Loading_en-US.srt 5.09 KB
  54. Extra (optional) Adding New Tokens to the Tokenizer.mp4 31.01 MB
  54. Extra (optional) Adding New Tokens to the Tokenizer_en-US.srt 3.96 KB
  55. Extra (optional) PyTorch Tricks for Faster LLM Training.mp4 41.43 MB
  55. Extra (optional) PyTorch Tricks for Faster LLM Training_en-US.srt 5.4 KB
  56. Extra (optional) Qwen3 from Scratch.mp4 55.1 MB
  56. Extra (optional) Qwen3 from Scratch_en-US.srt 8.08 KB
  57. Extra (optional) Gemma 3 270M from Scratch.mp4 37.62 MB
  57. Extra (optional) Gemma 3 270M from Scratch_en-US.srt 4.97 KB
  58. Extra (optional) Olmo 3 7B and 32B from Scratch.mp4 34.96 MB
  58. Extra (optional) Olmo 3 7B and 32B from Scratch_en-US.srt 5.32 KB
  59. Extra (optional) Chapter 5 with Qwen3 and Llama 3.2.mp4 36.82 MB
  59. Extra (optional) Chapter 5 with Qwen3 and Llama 3.2_en-US.srt 4.21 KB
  60. Extra (optional) Tiny Aya 3.35B from Scratch.mp4 33.96 MB
  60. Extra (optional) Tiny Aya 3.35B from Scratch_en-US.srt 4.83 KB
  61. Extra (optional) Qwen3.5 0.8B from Scratch.mp4 33.94 MB
  61. Extra (optional) Qwen3.5 0.8B from Scratch_en-US.srt 4.86 KB
  62. Extra (optional) Gemma 4 E2B and E4B from Scratch.mp4 38.16 MB
  62. Extra (optional) Gemma 4 E2B and E4B from Scratch_en-US.srt 5.38 KB
  63. Extra (optional) Training GPT with the Muon Optimizer.mp4 32.46 MB
  63. Extra (optional) Training GPT with the Muon Optimizer_en-US.srt 4.61 KB
  64. Extra (optional) Why CPU and MPS Give Different Results.mp4 22.93 MB
  64. Extra (optional) Why CPU and MPS Give Different Results_en-US.srt 2.74 KB
  ch05
  NOTICE.txt 558 B
  data
  scandal_in_bohemia.txt 45.41 KB
  gpt_download.py 5.83 KB
  gpt_weights.py 3.54 KB
  notebooks
  practice.ipynb 23.04 KB
  solution.ipynb 29.2 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  7 - Chapter 6 Fine-tuning for Classification
  6. Chapter 6 quiz Fine-tuning for classification.html 26.38 KB
  65. Intro & 6.1 Different categories of fine-tuning.mp4 14.78 MB
  65. Intro & 6.1 Different categories of fine-tuning_en-US.srt 1.49 KB
  66. 6.2 Preparing the dataset & 6.3 Creating data loaders.mp4 12.92 MB
  66. 6.2 Preparing the dataset & 6.3 Creating data loaders_en-US.srt 1.54 KB
  67. 6.4 Loading pretrained weights & 6.5 Adding a classification head.mp4 13.9 MB
  67. 6.4 Loading pretrained weights & 6.5 Adding a classification head_en-US.srt 1.56 KB
  68. 6.6 Classification loss and accuracy & 6.7 Fine-tuning on supervised data.mp4 10.83 MB
  68. 6.6 Classification loss and accuracy & 6.7 Fine-tuning on supervised data_en-US.srt 1.54 KB
  69. 6.8 Using the LLM as a spam classifier.mp4 13.95 MB
  69. 6.8 Using the LLM as a spam classifier_en-US.srt 1.87 KB
  70. Extra (optional) 19 Classification Fine-Tuning Experiments.mp4 40.32 MB
  70. Extra (optional) 19 Classification Fine-Tuning Experiments_en-US.srt 5.72 KB
  71. Extra (optional) Classifying 50k IMDb Movie Reviews.mp4 28.8 MB
  71. Extra (optional) Classifying 50k IMDb Movie Reviews_en-US.srt 3.58 KB
  72. Extra (optional) A Spam Classifier Web App.mp4 19.04 MB
  72. Extra (optional) A Spam Classifier Web App_en-US.srt 2.81 KB
  ch06
  NOTICE.txt 558 B
  gpt_download.py 5.83 KB
  gpt_weights.py 3.54 KB
  notebooks
  practice.ipynb 18.76 KB
  solution.ipynb 23.46 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  8 - Chapter 7 Fine-tuning to Follow Instructions
  7. Chapter 7 quiz Fine-tuning to follow instructions.html 25.89 KB
  73. Intro & 7.1 Introduction to instruction fine-tuning.mp4 15.27 MB
  73. Intro & 7.1 Introduction to instruction fine-tuning_en-US.srt 1.56 KB
  74. 7.2 Preparing an instruction dataset & 7.3 Organizing training batches.mp4 13.53 MB
  74. 7.2 Preparing an instruction dataset & 7.3 Organizing training batches_en-US.srt 1.65 KB
  75. 7.4 Data loaders & 7.5 Loading a pretrained LLM & 7.6 Fine-tuning.mp4 5.66 MB
  75. 7.4 Data loaders & 7.5 Loading a pretrained LLM & 7.6 Fine-tuning_en-US.srt 1.78 KB
  76. 7.7 Extracting and saving responses & 7.8 Evaluating the fine-tuned LLM.mp4 20.62 MB
  76. 7.7 Extracting and saving responses & 7.8 Evaluating the fine-tuned LLM_en-US.srt 2.82 KB
  77. Extra (optional) Cleaning an Instruction Dataset.mp4 31.42 MB
  77. Extra (optional) Cleaning an Instruction Dataset_en-US.srt 4.08 KB
  78. Extra (optional) Evaluating Answers with an LLM Judge.mp4 36.7 MB
  78. Extra (optional) Evaluating Answers with an LLM Judge_en-US.srt 4.28 KB
  79. Extra (optional) Preference Tuning with DPO from Scratch.mp4 55.73 MB
  79. Extra (optional) Preference Tuning with DPO from Scratch_en-US.srt 7.01 KB
  80. Extra (optional) Generating Instruction Data with an LLM.mp4 25.14 MB
  80. Extra (optional) Generating Instruction Data with an LLM_en-US.srt 3.4 KB
  81. Extra (optional) A Chat Interface for the Instruction Model.mp4 7.95 MB
  81. Extra (optional) A Chat Interface for the Instruction Model_en-US.srt 2.77 KB
  ch07
  NOTICE.txt 558 B
  gpt_download.py 5.83 KB
  gpt_weights.py 3.54 KB
  notebooks
  practice.ipynb 17.01 KB
  solution.ipynb 21.06 KB
  previous_chapters.py 9.67 KB
  requirements.txt 56 B
  9 - Appendix Fine-tuning with LoRA
  82. Appendix E Fine-Tuning with LoRA.mp4 40.92 MB
  82. Appendix E Fine-Tuning with LoRA_en-US.srt 5.66 KB

Description


Обучающие видео » Компьютерные видеоуроки и обучающие интерактивные DVD » Machine/Deep Learning, Neural Networks

Build an LLM from Scratch: Code a GPT in PyTorch

Год выпуска: 10/2026
Производитель: Udemy
Сайт производителя: https://www.udemy.com/course/build-an-llm-from-scratch-code-a-gpt-in-pytorch/
Автор: Thanh Vũ
Продолжительность: 4h 13m
Тип раздаваемого материала: Видеоурок
Язык: Английский
Описание: This course goes beyond simply using large language models like ChatGPT, Claude, Llama and Gemini to building one line by line in plain PyTorch and understanding every piece of it, using a Sherlock Holmes story, "A Scandal in Bohemia," as the running example. By the end, the learner's own code will pretrain a small GPT on the story and generate text in the style of Conan Doyle, turn a pretrained GPT-2 into a spam filter for text messages, and fine-tune it to follow instructions like a small personal assistant.

The course follows three stages: Stage 1 builds the foundation — what LLMs are, turning text into tokens and embeddings, coding self-attention and multi-head attention, and assembling a complete GPT model; Stage 2 is pretraining, covering the training loop, evaluation, temperature and top-k sampling, and loading the real GPT-2 weights; and Stage 3 is fine-tuning, with a text classifier and instruction fine-tuning with automatic evaluation. Every chapter comes with an animated video explaining the ideas with real numbers from real code, a practice notebook where learners write the key functions themselves while check cells immediately tell them whether the code is right, a quiz and an open challenge, and two appendices cover a PyTorch primer and parameter-efficient fine-tuning with LoRA, with more than forty optional extra videos going deeper into byte pair encoding from scratch, the KV cache, grouped-query attention, mixture of experts, Llama, Qwen and Gemma architectures, DPO and more. No GPU is needed since every notebook runs on a normal laptop, and there is no heavy math because every formula is shown with concrete numbers. The code is adapted from Sebastian Raschka's open source repository LLMs-from-scratch under the Apache License 2.0, his book "Build a Large Language Model (From Scratch)" is highly recommended for even more depth, and the examples, animations, exercises and quizzes were made for this course.
[spoiler="Содержание"]
1 - Welcome
1. Course introduction (04:56)
2. Appendix A A PyTorch Primer (08:07)

2 - Chapter 1 Understanding Large Language Models
3. Intro & 1.1 What is a large language model (01:15)
4. 1.2 Applications of LLMs & 1.3 Stages of building and using LLMs (01:27)
5. 1.4 Introducing the transformer architecture & 1.5 Utilizing large datasets (01:37)
6. 1.6 A closer look at the GPT architecture (01:25)
7. A counting language model & 1.7 Building a large language model (02:29)

3 - Chapter 2 Working with Text Data
8. Intro & 2.1 Understanding word embeddings (01:30)
9. 2.2 Tokenizing text & 2.3 Converting tokens into token IDs (01:17)
10. 2.4 Adding special context tokens & 2.5 Byte pair encoding (01:32)
11. 2.6 Data sampling with a sliding window (01:13)
12. 2.7 Creating token embeddings & 2.8 Encoding word positions (02:27)
13. Extra (optional) Byte Pair Encoding from Scratch (04:12)
14. Extra (optional) Comparing BPE Implementations (02:21)
15. Extra (optional) Embedding Layers vs. Linear Layers (01:46)
16. Extra (optional) The Data Loader with Plain Numbers (01:34)
17. Extra (optional) SimpleTokenizerV3 (01:14)

4 - Chapter 3 Coding Attention Mechanisms
18. Intro & 3.1 The problem with modeling long sequences (01:40)
19. 3.2 Capturing dependencies with attention & 3.3 Self-attention (02:31)
20. 3.4 Implementing self-attention with trainable weights (01:42)
21. 3.5 Hiding future words with causal attention (01:26)
22. 3.6 Extending single-head attention to multi-head attention (02:03)
23. Extra (optional) Nine Ways to Implement Multi-Head Attention (05:34)
24. Extra (optional) Understanding PyTorch Buffers (03:06)

5 - Chapter 4 Implementing a GPT Model from Scratch
25. Intro & 4.1 Coding an LLM architecture (02:22)
26. 4.2 Layer normalization & 4.3 Feed forward network with GELU (01:46)
27. 4.4 Shortcut connections & 4.5 The transformer block (01:24)
28. 4.6 Coding the GPT model (01:24)
29. 4.7 Generating text (01:41)
30. Extra (optional) FLOPs and Model FLOPs Utilization (02:36)
31. Extra (optional) The KV Cache (04:03)
32. Extra (optional) Grouped-Query Attention (GQA) (03:24)
33. Extra (optional) Multi-Head Latent Attention (MLA) (03:38)
34. Extra (optional) Sliding Window Attention (SWA) (03:24)
35. Extra (optional) Mixture of Experts (MoE) (04:11)
36. Extra (optional) Gated DeltaNet and Linear Attention (03:27)
37. Extra (optional) DeepSeek Sparse Attention (DSA) (03:06)
38. Extra (optional) Cross-Layer KV Sharing (03:13)

6 - Chapter 5 Pretraining on Unlabeled Data
39. Intro (01:20)
40. 5.1 Evaluating generative text models (01:20)
41. Inputs and targets & Cross-entropy and perplexity (02:04)
42. Training and validation data (01:32)
43. 5.2 Training an LLM & Loss curves and samples (02:16)
44. 5.3 Decoding strategies to control randomness & Temperature scaling (01:11)
45. Top-k sampling & 5.4 Saving and loading model weights (01:39)
46. 5.5 Loading pretrained weights from OpenAI & Loading weights into GPTModel (02:45)
47. Extra (optional) Alternative Ways to Load GPT-2 Weights (05:07)
48. Extra (optional) Pretraining GPT on Project Gutenberg (06:20)
49. Extra (optional) Warmup, Cosine Decay and Gradient Clipping (04:19)
50. Extra (optional) Hyperparameter Search for Pretraining (02:50)
51. Extra (optional) A Chat Interface for GPT-2 (03:27)
52. Extra (optional) From GPT to Llama 2, Llama 3 and Llama 3.2 (11:46)
53. Extra (optional) Memory-Efficient Weight Loading (04:38)
54. Extra (optional) Adding New Tokens to the Tokenizer (03:29)
55. Extra (optional) PyTorch Tricks for Faster LLM Training (05:07)
56. Extra (optional) Qwen3 from Scratch (07:28)
57. Extra (optional) Gemma 3 270M from Scratch (04:38)
58. Extra (optional) Olmo 3 7B and 32B from Scratch (04:55)
59. Extra (optional) Chapter 5 with Qwen3 and Llama 3.2 (03:59)
60. Extra (optional) Tiny Aya 3.35B from Scratch (04:27)
61. Extra (optional) Qwen3.5 0.8B from Scratch (04:22)
62. Extra (optional) Gemma 4 E2B and E4B from Scratch (04:53)
63. Extra (optional) Training GPT with the Muon Optimizer (04:11)
64. Extra (optional) Why CPU and MPS Give Different Results (02:34)

7 - Chapter 6 Fine-tuning for Classification
65. Intro & 6.1 Different categories of fine-tuning (01:13)
66. 6.2 Preparing the dataset & 6.3 Creating data loaders (01:30)
67. 6.4 Loading pretrained weights & 6.5 Adding a classification head (01:21)
68. 6.6 Classification loss and accuracy & 6.7 Fine-tuning on supervised data (01:21)
69. 6.8 Using the LLM as a spam classifier (01:40)
70. Extra (optional) 19 Classification Fine-Tuning Experiments (05:39)
71. Extra (optional) Classifying 50k IMDb Movie Reviews (03:38)
72. Extra (optional) A Spam Classifier Web App (02:26)

8 - Chapter 7 Fine-tuning to Follow Instructions
73. Intro & 7.1 Introduction to instruction fine-tuning (01:18)
74. 7.2 Preparing an instruction dataset & 7.3 Organizing training batches (01:21)
75. 7.4 Data loaders & 7.5 Loading a pretrained LLM & 7.6 Fine-tuning (01:39)
76. 7.7 Extracting and saving responses & 7.8 Evaluating the fine-tuned LLM (02:28)
77. Extra (optional) Cleaning an Instruction Dataset (03:52)
78. Extra (optional) Evaluating Answers with an LLM Judge (04:14)
79. Extra (optional) Preference Tuning with DPO from Scratch (06:54)
80. Extra (optional) Generating Instruction Data with an LLM (03:12)
81. Extra (optional) A Chat Interface for the Instruction Model (02:20)

9 - Appendix Fine-tuning with LoRA
82. Appendix E Fine-Tuning with LoRA (05:48)
[/spoiler]
Файлы примеров: не предусмотрены
Формат видео: MP4
Видео: AVC, 1920x1080, 16:9, 30fps, 1108kbps
Аудио: AAC, 44.1Hz, 128kbps, stereo
[spoiler="Скриншоты"]









[/spoiler]

Related Torrents

torrent name size uploader age seed leech
Build an AI Academic Tutor App with Local Ollama — Zero Cost [8/2026, ENG] Posted by unity321d in Other
664.59 MB unity321d 2 weeks 3 4
Udemy - Build an AI E-Commerce Chatbot with n8n Posted by freecoursewb in Other
450.4 MB freecoursewb 1 month 20 13
Java SE in Practice - Build an Application Posted by freecoursewb in Other
486.6 MB freecoursewb 3 months 12 6
Udemy - ISO 14001 - 2026 Lead Implementer - Build an EMS Posted by freecoursewb in Other
2.2 GB freecoursewb 4 months 6 2
DesignCode - Build an Animated App with Rive and SwiftUI Posted by freecoursewb in Other
520.8 MB freecoursewb 6 months 2 0