abhi9u
@abhi9u@lemmy.world
- Submitted 4 days ago to technology@lemmy.world | 0 comments
- A Selective Survey of Efficient Speculative Decoding Techniques for LLM Inferenceblog.codingconfessions.com ↗Submitted 4 weeks ago to technology@lemmy.world | 0 comments
- Submitted 1 month ago to technology@lemmy.world | 0 comments
- Submitted 2 months ago to technology@lemmy.world | 0 comments
- Are Function Calls Still Slow in Python? An Analysis of Recent Optimizations in CPythonblog.codingconfessions.com ↗Submitted 3 months ago to technology@lemmy.world | 13 comments
- Two Threads, One Core: How Simultaneous Multithreading Works Under the Hoodblog.codingconfessions.com ↗Submitted 3 months ago to technology@lemmy.world | 2 comments
- Submitted 11 months ago to programming@programming.dev | 0 comments
- Submitted 11 months ago to technology@lemmy.world | 0 comments
- Submitted 11 months ago to technology@lemmy.world | 0 comments
- Submitted 11 months ago to programming@programming.dev | 1 comment
- Submitted 1 year ago to programming@programming.dev | 10 comments
- Submitted 1 year ago to technology@lemmy.world | 0 comments
- Comment on An Analysis of DeepMind's 'Language Modeling Is Compression' Paper 1 year ago:
Yes, that makes much more sense.
- Comment on An Analysis of DeepMind's 'Language Modeling Is Compression' Paper 1 year ago:
Interesting. I’m just thinking aloud to understand this.
In this case, the models are looking at a few sequence of bytes in their context and are able to predict the next byte(s) with good accuracy, which allows efficient encoding. Most of our memories are associative, i.e. we associate them with some concept/name/idea. So, do you mean, our brain uses the concept to predict a token which gets decoded in the form of a memory?
- Comment on An Analysis of DeepMind's 'Language Modeling Is Compression' Paper 1 year ago:
Yes. They also mention that using such large models for compression is not practical because their size thwarts any amount of data you might want to compress. But this result gives a good picture into how generalized such large models are, and how well they are able to predict the next tokens for image/audio data at a high accuracy.
- Comment on An Analysis of DeepMind's 'Language Modeling Is Compression' Paper 1 year ago:
Do you mean the number of tokens in the LLM’s tokenizer, or the dictionary size of the compression algorithm?
The vocab size of the pretrained models is not mentioned anywhere in the paper. Although, they did conduct an experiment where they measured compression performance while using tokenizers of different vocabulary sizes.
If you meant the dictionary size of the compression algorithm, then there was no dictionary because they only used arithmetic coding to do the compression which doesn’t use dictionaries.
- Submitted 1 year ago to programming@programming.dev | 0 comments
- Submitted 1 year ago to technology@lemmy.world | 10 comments
- Comment on How to build a computer using origami 1 year ago:
Thank you!
- Comment on How to build a computer using origami 1 year ago:
I don’t know. I have found that the folks on Technology community appreciate many of my computer science posts. But a dedicated Comp Science community which is active, will be awesome.
- Comment on How to build a computer using origami 1 year ago:
Me too. :)
- Submitted 1 year ago to technology@lemmy.world | 10 comments
- Comment on How CPython Implements and Uses Bloom Filters for String Processing 1 year ago:
I have the same problem. The number of things I want to read and write about is scaling faster than I can tackle them :)
- Submitted 1 year ago to technology@lemmy.world | 2 comments
- Bloom Filters and Beyond: An Illustrated Introduction and Implementationcodeconfessions.substack.com ↗Submitted 1 year ago to technology@lemmy.world | 0 comments
- Understanding Immortal Objects in Python 3.12: A Deep Dive into Python Internalscodeconfessions.substack.com ↗Submitted 1 year ago to technology@lemmy.world | 15 comments
- How CPython Implements Reference Counting: Dissecting CPython Internalscodeconfessions.substack.com ↗Submitted 1 year ago to technology@lemmy.world | 0 comments
- Submitted 1 year ago to technology@lemmy.world | 1 comment