Hugging Face's logo
Jaward Sesay's picture
1 51 45

Jaward Sesay

Jaward
voxmenthe's profile picture Federic's profile picture ai-everyday's profile picture
·
https://github.com/Jaykef

AI & ML interests

Building Lectūra AI | CS Grad Student @BIT | AI/ML Research: Autonomous Agents, LLMs | First Paper (AutoAgents: A Framework for Automatic Agent Generation) Accepted @ IJCAI 2024 | Role Model Karpathy

Recent Activity

upvoted a paper 14 days ago
Group Sequence Policy Optimization
posted an update 21 days ago
Towards batch sizes too small to meter🎉 beautiful work! And my personal favorite so far - I adore peak performance at small/nano scale. Everyone deserves to run/train AGI locally:) our data, our god model! They showed that: - you can train LLMs (upto 1B params) with as low as batch_size=1. This is unconventional given small batch sizes can lead to unstable/spiky training runs. - you can have a stable train run with just vanilla SGD(stochastic gradient descent), no momentum required🤯 - small batch sizes are more robust to hyperparameters (i.e no worries with initialization) - smaller batch sizes outperforms (“better per-Flops performance”) larger batch sizes. “We recommend that practitioners training large models in memory-constrained settings exploit the benefits of small batch sizes rather than trying to emulate the large batch size setting (e.g., through gradient accumulation) typically used in industry.” I’ve been doing this for ages - my mantra: all my experiments must scale on my 8gb ram m2 before moving to gpu. IOW I love being gpu poor. Checkout my nanoAI algo repo: https://github.com/Jaykef/ai-algorithms, all notebooks run on memory as low as 8gb ram
updated a Space 23 days ago
Jaward/Lectura-Demo
View all activity

Organizations

MLX Community's profile picture