Actually Useful AI

2010 readers

7 users here now

Welcome! 🤖

Our community focuses on programming-oriented, hype-free discussion of Artificial Intelligence (AI) topics. We aim to curate content that truly contributes to the understanding and practical application of AI, making it, as the name suggests, "actually useful" for developers and enthusiasts alike.

Be an active member! 🔔

We highly value participation in our community. Whether it's asking questions, sharing insights, or sparking new discussions, your engagement helps us all grow.

What can I post? 📝

In general, anything related to AI is acceptable. However, we encourage you to strive for high-quality content.

What is not allowed? 🚫

🔊 Sensationalism: "How I made $1000 in 30 minutes using ChatGPT - the answer will surprise you!"
♻️ Recycled Content: "Ultimate ChatGPT Prompting Guide" that is the 10,000th variation on "As a (role), explain (thing) in (style)"
🚮 Blogspam: Anything the mods consider crypto/AI bro success porn sigma grindset blogspam

General Rules 📜

Members are expected to engage in on-topic discussions, and exhibit mature, respectful behavior. Those who fail to uphold these standards may find their posts or comments removed, with repeat offenders potentially facing a permanent ban.

While we appreciate focus, a little humor and off-topic banter, when tasteful and relevant, can also add flavor to our discussions.

Related Communities 🌐

General

Chat

[email protected]

Image

Open Source

[email protected]

Please message @[email protected] if you would like us to add a community to this list.

Icon base by Lord Berandas under CC BY 3.0 with modifications to add a gradient

founded 1 year ago

MODERATORS

sisyphean

TinyStories: How Small Can Language Models Be and Still Speak Coherent English? (arxiv.org)

submitted 1 year ago* (last edited 1 year ago) by sisyphean to c/auai

3 comments fedilink hide all child comments

Quote:

In this work, we introduce TinyStories, a synthetic dataset of short stories that only contain words that a typical 3 to 4-year-olds usually understand, generated by GPT-3.5 and GPT-4. We show that TinyStories can be used to train and evaluate LMs that are much smaller than the state-of-the-art models (below 10 million total parameters), or have much simpler architectures (with only one transformer block), yet still produce fluent and consistent stories with several paragraphs that are diverse and have almost perfect grammar, and demonstrate reasoning capabilities.

Related:

Models (you can try them online):
- TinyStories-1M
- TinyStories-33M
An interview with the authors (highly recommended): The Tiny Model Revolution with Ronen Eldan and Yuanzhi Li of Microsoft Research

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

[–] [email protected] 2 points 1 year ago* (last edited 1 year ago)

I've had a play with these models and the dataset.

They're under-trained, you can squeeze about 10% more performance out of them.
They're trained on the GPT3.5 generated dataset, and there's a GPT4 generated dataset available on Huggingface
The GPT4 dataset (I haven't looked at the GPT3.5 dataset) has random bad Unicode, misspellings, missing spaces, etc
Because of 3, the tokenization isn't great

Given all that, retraining on a cleaned dataset may give even more impressive results.