As featured in
Follow
Overview
News
Technologies
Salaries
Products
People
Growth
Offices
Financials
Overview
Hi, I'm Tyler Romero.. I am a Member of Technical Staff on the MAI Superintelligence Team. Previously, I was a Research Engineer at the Allen Institute (Ai2), where I worked on open language modeling.
News
Computing sharding with einsum : ezyang's blog
Edward Yang's insightful blog on distributed ML systems. I especially like Computing sharding with einsum .
Read more
Report
NanoGPT Speedrun Worklog
I saw some really awesome GPT-2 speedrun results from people like Keller Jordan , Fern , Braden Koszarsk...
Read more
Report
Look College honors outstanding seniors
The Dwight Look College of Engineering at Texas A&M University honored seven students with its Craig C. Brown Outstanding Senior Engineering Award during a banquet Oct. 1 at the Memorial Student Center on the Texas A&M campus.
Read more
Report
Reducing VRAM Footprint in PPO and GRPO Using Selective Log-Softmax
When training language models, we often need to convert logits (raw model outputs) into log probabilities. The standard approach uses log_softmax , which computes a log probability for every token in the vocabulary at every position in the sequence: def n
Read more
Report
An Extension to BADGE Active Learning for Variable-Sized Batches
Batch Active learning by Diverse Gradient Embeddings (BADGE) is a simple and effective batch-based active learning method for neural networks that has been empirically shown to outperform other active learning approaches in a variety of settings. BADGE se
Read more
Report
Pro access
Upgrade to see all 12 mentions
Upgrade to a paid plan to read every media mention of this company - funding news, awards, product launches and press releases from all the outlets writing about it.
Every media mention and press release
Funding news, awards and product launches
Fresh coverage from every outlet writing about the company
Upgrade now
Cancel anytime. Secure checkout. Instant activation.
