Brad's picture

2 1 7

Brad

Firepal3D

AI & ML interests

None yet

Recent Activity

reacted to grimjim's post with 🔥 27 days ago

I recently have been looking at a paper titled "Why Warmup the Learning Rate? Underlying Mechanisms and Improvements", by Dayal Singh Kalra and Maissam Barkeshli, and was struck by "warmup" being analogous to simulated annealing. https://arxiv.org/abs/2406.09405 Taking the physical analogy further, the "warmup" is a stochastic process to knock the system out of current local minima, allowing easier transition toward newer minima. It works because it reduces "fit" and therefore "friction".

liked a dataset about 2 months ago

inclinedadarsh/nl-to-regex

View all activity

Organizations

None yet

Firepal3D's activity

liked a dataset about 2 months ago

inclinedadarsh/nl-to-regex

Viewer • Updated Mar 24 • 824 • 55 • 2

liked 2 models 8 months ago

terrycraddock/Reflection-Llama-3.1-8B

Text Generation • Updated Sep 14, 2024 • 148 • • 16

mradermacher/Reflection-Llama-3.1-8B-i1-GGUF

Updated Sep 9, 2024 • 964 • 2

liked a model 10 months ago

qwp4w3hyb/Codestral-22B-v0.1-iMat-GGUF

Text Generation • Updated Jun 1, 2024 • 224 • 3

liked a model 12 months ago

WaefreBeorn/AVGN_James_Rolfe

Updated Jul 6, 2023 • 1

liked a model about 2 years ago

bigscience/bloom

Text Generation • Updated Jul 28, 2023 • 4.83k • 4.89k

liked a Space about 2 years ago

ZoeDepth

Create 3D models from images