Name: See TensorFlow’s activity on LinkedIn
Uploaded: 2025-01-31T14:04:14.831Z
Duration: 57 s
Channel: TensorFlow
Description: From research to reality: Gemma and the power of post-training. 💪→ https://goo.gle/4hDfh4S Google DeepMind’s research scientist Léonard Hussenot details: 🔍 How Gemma facilitates post-training research 🚀 Leverage Best-of-N Distillation (BOND) for model efficiency 🏆 Improve reward models with weight averaging Watch the #GemmaDeveloperDay session to learn more.

TensorFlow reposted this

Google for Developers

2,200,341 followers

2mo Edited

From research to reality: Gemma and the power of post-training. 💪→ https://goo.gle/4hDfh4S Google DeepMind’s research scientist Léonard Hussenot details: 🔍 How Gemma facilitates post-training research 🚀 Leverage Best-of-N Distillation (BOND) for model efficiency 🏆 Improve reward models with weight averaging Watch the #GemmaDeveloperDay session to learn more.

5 Comments

SHAN E ALAM

Artificial Intelligence Developer, Python, IBM Developer

2mo

Excellent

Avinash Pandey

Pursuing BS in Data Science And Applications From Indian Institute of Technology, Madras

2mo

Insightful

mahmoud rfaat

2mo

Why does Google show you many search results when you search... that are far from what you are searching for, and you also have to search the results... just because your search words are similar to the words of the topics... Why isn't there Search (rotating classifier)

Sarthak Singhchouhan

Attended Dropper

2mo

Very informative

Scott Campbell

Sr. SWE ++ Roc Lang, Rust, Zig, JS/TS, C# ++ Communication & Design

2mo

Useful tips

See more comments

To view or add a comment, sign in

TensorFlow’s Post

Explore topics