Sam Joshua's picture
1 1

Sam Joshua

SamJoshua
ยท

AI & ML interests

None yet

Recent Activity

Organizations

None yet

SamJoshua's activity

reacted to garrethlee's post with ๐Ÿ”ฅ about 1 month ago
view post
Post
1912
The latest o1 model from OpenAI is still unable to answer 9.11 > 9.9 correctly ๐Ÿค”

A possible explanation? Tokenization - and our latest work investigates how it affects a model's ability to do math!

In this blog post, we discuss:
๐Ÿ”ข The different ways numbers are tokenized in modern LLMs
๐Ÿงช Our detailed approach in comparing these various methods
๐Ÿฅช How we got a free boost in arithmetic performance by adding a few lines of code to the base Llama 3 tokenizer
๐Ÿ‘‘ and a definitive, best tokenization method for math in LLMs!

Check out our work here: huggingface/number-tokenization-blog
  • 2 replies
ยท
upvoted an article 6 months ago
view article
Article

From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate

โ€ข 45