Sam Joshua
SamJoshua
AI & ML interests
None yet
Recent Activity
reacted
to
garrethlee's
post
with 🔥
24 days ago
The latest o1 model from OpenAI is still unable to answer 9.11 > 9.9 correctly 🤔
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:
🔢 The different ways numbers are tokenized in modern LLMs
🧪 Our detailed approach in comparing these various methods
🥪 How we got a free boost in arithmetic performance by adding a few lines of code to the base Llama 3 tokenizer
👑 and a definitive, best tokenization method for math in LLMs!
Check out our work here: https://huggingface.co/spaces/huggingface/number-tokenization-blog
Organizations
None yet
SamJoshua's activity
No public activity