English
English Indonesia Türkçe Deutsch Español Português Pусский Français Italiano Nederlands Polski العربية ไทย Tiếng Việt 繁體中文 简体中文 日本語 한국어
AdaptiveML's profile picture. Evaluate, tune, and serve the best LLMs for your business. If you can measure it, reinforcement learning can optimize it.

Adaptive ML

@AdaptiveML

Evaluate, tune, and serve the best LLMs for your business. If you can measure it, reinforcement learning can optimize it.

65Posts 370Followers 30Following
Pinned
AdaptiveML's profile picture.
Adaptive ML
 @AdaptiveML
Jul 22

Using Adaptive Engine, @SKtelecom tuned open models as small as Gemma 3 4B to exceed frontier performance (GPT-4.1, 3.7 Sonnet, and o4-mini) at multilingual content moderation. Our research 📃 and full results 👇

AdaptiveML's tweet image. Using Adaptive Engine, @SKtelecom tuned open models as small as Gemma 3 4B to exceed frontier performance (GPT-4.1, 3.7 Sonnet, and o4-mini) at multilingual content moderation. Our research 📃 and full results 👇
2
15
28
9
4K
Adaptive ML reposted
googleaidevs's profile picture.
Google AI Developers
@googleaidevs
Aug 21

Some interesting use cases from @AdaptiveML powered by Gemma 🧵⬇️

5
12
187
93
24K
AdaptiveML's profile picture.
Adaptive ML
 @AdaptiveML
Aug 12

"Pre-training gets you knowledge, post-training gets you wisdom" - Julien Launay. 🎯 In this @SuperDataSci episode, @AdaptiveML ML CEO @slippylolo reveals how RLAIF, RLVR and synthetic data are pushing the performance of SLMs to the frontier. youtube.com/watch?v=ocVCDH…

AdaptiveML's tweet card. 913: LLM Pre-Training and Post-Training 101 — with Julien Launay

youtube.com

YouTube

913: LLM Pre-Training and Post-Training 101 — with Julien Launay

Source: youtube.com
1
2
5
2
829
Adaptive ML reposted
superdatasci's profile picture.
SuperDataScience
@superdatasci
Aug 12

Julien Launay launched Adaptive to give data science teams in business enterprises their “RLOps tooling” to make reinforcement learning easier. Talking to @JonKrohnLearns, Julien says, “Most of our users are data scientists who write Python codes to interface with the system”.…

superdatasci's tweet image. Julien Launay launched Adaptive to give data science teams in business enterprises their “RLOps tooling” to make reinforcement learning easier. Talking to @JonKrohnLearns, Julien says, “Most of our users are data scientists who write Python codes to interface with the system”.…
1
3
5
0
442
AdaptiveML's profile picture.
Adaptive ML
 @AdaptiveML
Aug 6

We're proud to announce that gpt-oss-120b and gpt-oss-20b are now available on Adaptive Engine. Reinforcement fine-tune, evaluate, and serve @OpenAI's first open-weight models since GPT-2 🚀

AdaptiveML's tweet image. We're proud to announce that gpt-oss-120b and gpt-oss-20b are now available on Adaptive Engine. Reinforcement fine-tune, evaluate, and serve @OpenAI's first open-weight models since GPT-2 🚀
0
0
1
1
216
Adaptive ML reposted
_philschmid's profile picture.
Philipp Schmid
@_philschmid
Jul 30

Mind-blowing! 🤯 Gemma just showed how a small, open models can run circles around the big ones. @SKtelecom and @AdaptiveML customized Gemma 3 4B to be cheaper, faster, and more accurate than models twice its size. Goal: Create a highly accurate, low-latency content moderation…

_philschmid's tweet image. Mind-blowing! 🤯 Gemma just showed how a small, open models can run circles around the big ones. @SKtelecom and @AdaptiveML customized Gemma 3 4B to be cheaper, faster, and more accurate than models twice its size. Goal: Create a highly accurate, low-latency content moderation…
6
23
151
88
8K
Adaptive ML reposted
osanseviero's profile picture.
Omar Sanseviero
@osanseviero
Jul 26

SK Telecom + @AdaptiveML trained Gemma 3 4B with PPO obtaining impressive results, specially for a model of such size Learn more about how they did this adaptive-ml.com/post/sk-teleco…

osanseviero's tweet image. SK Telecom + @AdaptiveML trained Gemma 3 4B with PPO obtaining impressive results, specially for a model of such size Learn more about how they did this adaptive-ml.com/post/sk-teleco…
1
12
48
19
3K

United States Trends

Something went wrong.


Something went wrong.