Comments (2)
These are good questions!
I am not sure which one is better: .reshape() or .view()?
I wouldn't say one is better than the other but yeah, they are subtly different
-
The
.view
method returns a new tensor with the same data as the original tensor. -
The
.reshape
method and can handle non-contiguous tensors and will automatically make a contiguous copy of the tensor if necessary.
I've been using .view
in the main book for consistency (and because it's been the original method in PyTorch for reshaping before .reshape
was added later).
But yeah, it requires the .contiguous
here. (Maybe not a bad thing though for educational purposes.)
I will update it here in bonus material as well, changing .reshape
to .view
, to make it more consistent.
.unbind(0) is not necessary (the shape of queries, keys, values does not change without it), is it a speed concern?
I think you might be right. I will investigate ...
According to the equivalent implementation in
F.scaled_dot_product_attention()
, it seems like self.proj() is missing at the end:
Good catch, I may have missed that one. Will update it!
from llms-from-scratch.
Looks like adding the missing projection layer had only minimal impact on the runtime. You can find the updated results in #131 . Thanks again for all your thoughtful question. Please feel free to reopen this or post new issues if you have any follow-up questions.
from llms-from-scratch.
Related Issues (20)
- In 3.3.1, there seems to be a missing image between "The attention weights and context vector calculation are summarized in the figure below:" and "The code below walks through the figure above step by step." HOT 1
- RuntimeError: size mismatch - ch05/03_bonus_pretraining_on_gutenberg HOT 2
- book feedback HOT 1
- The definition of stride is confusing in 2.6 HOT 3
- Difference btwn book and repo HOT 1
- suggestion of adding torch.profile
- do have a doc for hardware specs HOT 2
- ch06/03_bonus_imdb-classification HOT 16
- Expected all tensors to be on the same device HOT 1
- Throwing error for longer textual data like 9599 HOT 4
- Inconsistencies in unsqueeze operation description in the book and in notebook and its necessity (3.6.2 Implementing multi-head attention with weight splits) HOT 4
- Solution for Exercise 3.3 is included in the notebook with main code (3.6.2 Implementing multi-head attention with weight splits) HOT 1
- Inconsistencies in MHA Wrapper Implementation Between Chapter 3 Main Content and Bonus Material HOT 1
- Offering Chinese Translation for 'Build a Large Language Model From Scratch HOT 3
- Chapter 5 - Context Size and the DataLoaders HOT 2
- Feedback: Stripe output from notebook HOT 2
- About endoftext in ch05/03_bonus_pretraining_on_gutenberg/pretraining_simple.py HOT 14
- Contributions for Chinese simplified version HOT 4
- {Q} : Replacing the LlamaDecoderLayer Class hugging Face With New LongNet
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llms-from-scratch.