LocalLLaMA

3525 readers

4 users here now

Welcome to LocalLLaMA! Here we discuss running and developing machine learning models at home. Lets explore cutting edge open source neural network technology together.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support each other and share our enthusiasm in a positive constructive way.

Rules:

Rule 1 - No harassment or personal character attacks of community members. I.E no namecalling, no generalizing entire groups of people that make up our community, no baseless personal insults.

Rule 2 - No comparing artificial intelligence/machine learning models to cryptocurrency. I.E no comparing the usefulness of models to that of NFTs, no comparing the resource usage required to train a model is anything close to maintaining a blockchain/ mining for crypto, no implying its just a fad/bubble that will leave people with nothing of value when it burst.

Rule 3 - No comparing artificial intelligence/machine learning to simple text prediction algorithms. I.E statements such as "llms are basically just simple text predictions like what your phone keyboard autocorrect uses, and they're still using the same algorithms since <over 10 years ago>.

Rule 4 - No implying that models are devoid of purpose or potential for enriching peoples lives.

founded 2 years ago

MODERATORS

[email protected]

Single Digit tokenization improves LLM math abilities by up to 70x (twitter.com)

submitted 2 years ago by [email protected] to c/[email protected]

2 comments fedilink hide all child comments

From the tweet (minus pictures):

Language models are bad a basic math.

GPT-4 has right around 0% accuracy rate on 5 digit multiplication.

Most open models can't even add. Why is that?

There are a few reasons why numbers are hard. The main one is Tokenization. When training a tokenizer from scratch, you take a large corpus of text and find the minimal byte-pair encoding for a chosen vocabulary size.

This means, however, that numbers will almost certainly not have unique token representations. "21" could be a single token, or ["2", "1"]. 143 could be ["143"] or ["14", "3"] or any other combination.

A potential fix here would be to force single digit tokenization. The state of the art for the last few years is to inject a space between every digit when creating the tokenizer and when running the model. This means 143 would always be tokenized as ["1", "4", "3"].

This helps boost performance, but wastes tokens while not fully fixing the problem.

A cool fix might be xVal! This work by The Polymathic AI Collaboration suggests a generic [NUM] token which is then scaled by the actual value of the number!

If you look at the red lines in the image above, you can get an intuition for how that might work.

It doesn't capture a huge range or high fidelity (e.g., 7.4449 vs 7.4448) but they showcase some pretty convincing results on sequence prediction problems that are primarily numeric.

For example, they want to train a sequence model on GPS conditioned temperature forecasting

They found a ~70x improvement over standard vanilla baselines and a 2x improvement over really strong baselines.

One cool side effect is that deep neural networks might be really good at regression problems using this encoding scheme!

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 2 points 2 years ago

This is really interesting, and I suspect we'll be seeing a lot more papers like this in the next few years. There's a lot of room for these sorts of tokenization optimizations right now.