Этот материал находится в платной подписке. Оформи премиум подписку и смотри или слушай Master and Build Large Language Models, а также все другие курсы, прямо сейчас!
Премиум
  1. Урок 1. 00:21:10
    1.1. Python Environment Setup Video
  2. Урок 2. 00:06:28
    1.2. Foundations to Build a Large Language Model (From Scratch)
  3. Урок 3. 01:07:40
    2.1. Prerequisites to Chapter 2 (1
  4. Урок 4. 00:14:10
    2.2. Tokenizing text
  5. Урок 5. 00:09:59
    2.3. Converting tokens into token IDs
  6. Урок 6. 00:06:36
    2.4. Adding special context tokens
  7. Урок 7. 00:13:40
    2.5. Byte pair encoding
  8. Урок 8. 00:23:16
    2.6. Data sampling with a sliding window
  9. Урок 9. 00:08:37
    2.7. Creating token embeddings
  10. Урок 10. 00:12:23
    2.8. Encoding word positions
  11. Урок 11. 01:14:17
    3.1. Prerequisites to Chapter 3 (1
  12. Урок 12. 00:41:10
    3.2. A simple self-attention mechanism without trainable weights | Part 1
  13. Урок 13. 00:11:43
    3.3. A simple self-attention mechanism without trainable weights | Part 2
  14. Урок 14. 00:20:00
    3.4. Computing the attention weights step by step
  15. Урок 15. 00:08:31
    3.5. Implementing a compact self-attention Python class
  16. Урок 16. 00:11:37
    3.6. Applying a causal attention mask
  17. Урок 17. 00:05:38
    3.7. Masking additional attention weights with dropout
  18. Урок 18. 00:08:53
    3.8. Implementing a compact causal self-attention class
  19. Урок 19. 00:12:05
    3.9. Stacking multiple single-head attention layers
  20. Урок 20. 00:16:47
    3.10. Implementing multi-head attention with weight splits
  21. Урок 21. 01:11:23
    4.1. Prerequisites to Chapter 4 (1
  22. Урок 22. 00:14:00
    4.2. Coding an LLM architecture
  23. Урок 23. 00:22:14
    4.3. Normalizing activations with layer normalization
  24. Урок 24. 00:16:19
    4.4. Implementing a feed forward network with GELU activations
  25. Урок 25. 00:10:52
    4.5. Adding shortcut connections
  26. Урок 26. 00:12:14
    4.6. Connecting attention and linear layers in a transformer block
  27. Урок 27. 00:12:45
    4.7. Coding the GPT model
  28. Урок 28. 00:17:47
    4.8. Generating text
  29. Урок 29. 00:23:58
    5.1. Prerequisites to Chapter 5
  30. Урок 30. 00:17:32
    5.2. Using GPT to generate text
  31. Урок 31. 00:27:14
    5.3. Calculating the text generation loss: cross entropy and perplexity
  32. Урок 32. 00:24:52
    5.4. Calculating the training and validation set losses
  33. Урок 33. 00:27:04
    5.5. Training an LLM
  34. Урок 34. 00:03:37
    5.6. Decoding strategies to control randomness
  35. Урок 35. 00:13:43
    5.7. Temperature scaling
  36. Урок 36. 00:08:20
    5.8. Top-k sampling
  37. Урок 37. 00:10:51
    5.9. Modifying the text generation function
  38. Урок 38. 00:04:24
    5.10. Loading and saving model weights in PyTorch
  39. Урок 39. 00:20:04
    5.11. Loading pretrained weights from OpenAI
  40. Урок 40. 00:39:21
    6.1. Prerequisites to Chapter 6
  41. Урок 41. 00:26:58
    6.2. Preparing the dataset
  42. Урок 42. 00:16:08
    6.3. Creating data loaders
  43. Урок 43. 00:10:11
    6.4. Initializing a model with pretrained weights
  44. Урок 44. 00:15:38
    6.5. Adding a classification head
  45. Урок 45. 00:22:32
    6.6. Calculating the classification loss and accuracy
  46. Урок 46. 00:33:36
    6.7. Fine-tuning the model on supervised data
  47. Урок 47. 00:11:07
    6.8. Using the LLM as a spam classifier
  48. Урок 48. 00:15:48
    7.1. Preparing a dataset for supervised instruction fine-tuning
  49. Урок 49. 00:23:45
    7.2. Organizing data into training batches
  50. Урок 50. 00:07:31
    7.3. Creating data loaders for an instruction dataset
  51. Урок 51. 00:07:48
    7.4. Loading a pretrained LLM
  52. Урок 52. 00:20:02
    7.5. Fine-tuning the LLM on instruction data
  53. Урок 53. 00:09:40
    7.6. Extracting and saving responses
  54. Урок 54. 00:21:57
    7.7. Evaluating the fine-tuned LLM