Companies Home Search Profile

Build a Large Language Model from Scratch (early access), Video Edition

Focused View

8:12:00

0 View
  • Appendix A. Automatic differentiation made easy.mp4
    03:54
  • Appendix A. A typical training loop.mp4
    07:25
  • Appendix A. Exercise answers.mp4
    01:45
  • Appendix A. Further reading.mp4
    02:08
  • Appendix A. Implementing multilayer neural networks.mp4
    08:47
  • Appendix A. Introduction to PyTorch.mp4
    15:16
  • Appendix A. Optimizing training performance with GPUs.mp4
    17:11
  • Appendix A. Saving and loading models.mp4
    01:50
  • Appendix A. Seeing models as computation graphs.mp4
    02:26
  • Appendix A. Setting up efficient data loaders.mp4
    08:19
  • Appendix A. Summary.mp4
    01:21
  • Appendix A. Understanding tensors.mp4
    07:20
  • Appendix D. Adding Bells and Whistles to the Training Loop.mp4
    02:58
  • Appendix D. Cosine decay.mp4
    01:46
  • Appendix D. Gradient clipping.mp4
    03:16
  • Appendix D. The modified training function.mp4
    01:29
  • Appendix E. Initializing the model.mp4
    01:14
  • Appendix E. Parameter-efficient Finetuning with LoRA.mp4
    04:44
  • Appendix E. Parameter-efficient finetuning with LoRA (1).mp4
    09:04
  • Appendix E. Preparing the dataset.mp4
    01:30
  • Chapter 1. Applications of LLMs.mp4
    02:11
  • Chapter 1. A closer look at the GPT architecture.mp4
    05:23
  • Chapter 1. Building a large language model.mp4
    01:49
  • Chapter 1. Introducing the transformer architecture.mp4
    07:02
  • Chapter 1. Stages of building and using LLMs.mp4
    04:33
  • Chapter 1. Summary.mp4
    02:04
  • Chapter 1. Understanding Large Language Models.mp4
    08:35
  • Chapter 1. Utilizing large datasets.mp4
    03:53
  • Chapter 2. Adding special context tokens.mp4
    05:57
  • Chapter 2. Byte pair encoding.mp4
    04:44
  • Chapter 2. Converting tokens into token IDs.mp4
    05:38
  • Chapter 2. Creating token embeddings.mp4
    05:25
  • Chapter 2. Data sampling with a sliding window.mp4
    09:15
  • Chapter 2. Encoding word positions.mp4
    07:09
  • Chapter 2. Summary.mp4
    01:51
  • Chapter 2. Tokenizing text.mp4
    06:07
  • Chapter 2. Working with Text Data.mp4
    08:09
  • Chapter 3. Attending to different parts of the input with self-attention.mp4
    15:20
  • Chapter 3. Capturing data dependencies with attention mechanisms.mp4
    03:01
  • Chapter 3. Coding Attention Mechanisms.mp4
    06:43
  • Chapter 3. Extending single-head attention to multi-head attention.mp4
    14:12
  • Chapter 3. Hiding future words with causal attention.mp4
    12:44
  • Chapter 3. Implementing self-attention with trainable weights.mp4
    17:54
  • Chapter 3. Summary.mp4
    01:44
  • Chapter 4. Adding shortcut connections.mp4
    05:36
  • Chapter 4. Coding the GPT model.mp4
    09:28
  • Chapter 4. Connecting attention and linear layers in a transformer block.mp4
    05:37
  • Chapter 4. Generating text.mp4
    08:19
  • Chapter 4. Implementing a GPT model from Scratch To Generate Text.mp4
    11:53
  • Chapter 4. Implementing a feed forward network with GELU activations.mp4
    06:51
  • Chapter 4. Normalizing activations with layer normalization.mp4
    10:30
  • Chapter 4. Summary.mp4
    01:29
  • Chapter 5. Decoding strategies to control randomness.mp4
    12:10
  • Chapter 5. Loading and saving model weights in PyTorch.mp4
    03:30
  • Chapter 5. Loading pretrained weights from OpenAI.mp4
    08:59
  • Chapter 5. Pretraining on Unlabeled Data.mp4
    29:18
  • Chapter 5. Summary.mp4
    01:10
  • Chapter 5. Training an LLM.mp4
    07:44
  • Chapter 6. Adding a classification head.mp4
    09:57
  • Chapter 6. Calculating the classification loss and accuracy.mp4
    05:25
  • Chapter 6. Creating data loaders.mp4
    07:21
  • Chapter 6. Finetuning for Classification.mp4
    04:59
  • Chapter 6. Finetuning the model on supervised data.mp4
    06:12
  • Chapter 6. Initializing a model with pretrained weights.mp4
    02:18
  • Chapter 6. Preparing the dataset.mp4
    04:16
  • Chapter 6. Summary.mp4
    01:25
  • Chapter 6. Using the LLM as a spam classifier.mp4
    01:50
  • Chapter 7. Conclusions.mp4
    03:22
  • Chapter 7. Creating data loaders for an instruction dataset.mp4
    03:53
  • Chapter 7. Evaluating the finetuned LLM.mp4
    10:22
  • Chapter 7. Extracting and saving responses.mp4
    06:00
  • Chapter 7. Finetuning the LLM on instruction data.mp4
    07:06
  • Chapter 7. Finetuning to Follow Instructions.mp4
    03:42
  • Chapter 7. Loading a pretrained LLM.mp4
    04:34
  • Chapter 7. Organizing data into training batches.mp4
    15:09
  • Chapter 7. Preparing a dataset for supervised instruction finetuning.mp4
    05:15
  • Chapter 7. Summary.mp4
    01:14
  • More details


    User Reviews
    Rating
    0
    0
    0
    0
    0
    average 0
    Total votes0
    Focused display
    Category
    O'Reilly Media is an American learning company established by Tim O'Reilly that publishes books, produces tech conferences, and provides an online learning platform. Its distinctive brand features a woodcut of an animal on many of its book covers.
    • language english
    • Training sessions 77
    • duration 8:12:00
    • Release Date 2024/11/03