Hugging Face's logo
Sam Joshua's picture
1 2

Sam Joshua

SamJoshua
sigridjineth's profile picture
Ā·

AI & ML interests

None yet

Recent Activity

upvoted an article 30 days ago
Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment
reacted to garrethlee's post with šŸ”„ 3 months ago
The latest o1 model from OpenAI is still unable to answer 9.11 > 9.9 correctly šŸ¤” 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: šŸ”¢ The different ways numbers are tokenized in modern LLMs šŸ§Ŗ Our detailed approach in comparing these various methods šŸ„Ŗ How we got a free boost in arithmetic performance by adding a few lines of code to the base Llama 3 tokenizer šŸ‘‘ and a definitive, best tokenization method for math in LLMs! Check out our work here: https://huggingface.co/spaces/huggingface/number-tokenization-blog
upvoted an article 8 months ago
From DeepSpeed to FSDP and Back Again with Hugging Face Accelerate
View all activity

Organizations

None yet

datasets

None public yet