yushun0410 (yushun zhang)

upvoted 2 collections 4 days ago

Qwen2.5

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated Sep 18 • 382

Qwen2.5-Math

Collection

Math-specific model series based on Qwen2.5 • 9 items • Updated Sep 23 • 52

Reacted to their post with 🔥🚀👍 5 months ago

Post

4609

Hi Huggingfacers!

Thrilled to introduce Adam-mini, an optimizer that achieves on-par or better performance than AdamW with 45% to 50% less memory footprint. Adam-mini can also achieve 49.5% higher throughput than AdamW on Llama2-7B pre-training.

The design of Adam-mini is inspired by certain Hessian structures we observed on Transformers.

Feel free to try it out! Try switching to Adam-mini with the same hyperparams of AdamW, it would work with only half memory. Hope Adam-mini can help save time, cost, and energy in your tasks!

Paper: "Adam-mini: Use Fewer Learning Rates To Gain More" https://arxiv.org/abs/2406.16793

Code: https://github.com/zyushun/Adam-mini

1 reply

·

posted an update 5 months ago

Post

4609

Hi Huggingfacers!

Thrilled to introduce Adam-mini, an optimizer that achieves on-par or better performance than AdamW with 45% to 50% less memory footprint. Adam-mini can also achieve 49.5% higher throughput than AdamW on Llama2-7B pre-training.

The design of Adam-mini is inspired by certain Hessian structures we observed on Transformers.

Feel free to try it out! Try switching to Adam-mini with the same hyperparams of AdamW, it would work with only half memory. Hope Adam-mini can help save time, cost, and energy in your tasks!

Paper: "Adam-mini: Use Fewer Learning Rates To Gain More" https://arxiv.org/abs/2406.16793

Code: https://github.com/zyushun/Adam-mini