Predibase by Rubrik (@predibase) / X

Predibase by Rubrik

613 posts

Predibase by Rubrik

@predibase

Confidently deploy AI with a unified platform for agent monitoring, governance, and remediation.

San Francisco, CA

Joined November 2020

Pinned
Predibase by Rubrik
@predibase
Oct 22, 2025
Unleash #agents, not risk! 🤖 @rubrikInc is the first to provide a true enterprise control layer that transforms #AI chaos into operational excellence. Learn more about Rubrik Agent Cloud powered by @predibase AI Infra 👉 go.rbrk.co/tnbcp
GIF
493
Predibase by Rubrik
@predibase
Mar 19, 2025
Today we're thrilled to announce the first end-to-end platform for Reinforcement Fine-Tuning. With just a dozen labeled data points, you can outperform #OpenAI o1 and #DeepSeekR1 on complex tasks. Built on the #GRPO methodology that DeepSeek-R1 popularized, our platform delivers
00:00
1M
Predibase by Rubrik
@predibase
Feb 20, 2024
🚀 We fine-tuned 27 adapters using #Mistral-7B on Predibase for < $8.00 each and 25 of them rival or outperform #GPT4 📊 Check out our blog to see benchmarks, learn how we did it & get the link to download the #LLMs on @huggingface #TheFutureIsFineTuned pbase.ai/49Hrwtn
15K
Predibase by Rubrik
@predibase
Mar 18, 2024
🎉 Excited to share the launch of the @DeepLearningAI course Efficiently Serving #LLMs developed w/ @predibase CTO @TravisAddair 🎉 ✅ Implement a modern inference stack w/ caching, batching & #quantization ✅ Intro to #LoRA adapters ✅...and much more
Efficiently Serving LLMs
From deeplearning.ai
950
Predibase by Rubrik
@predibase
Mar 19, 2025
Replying to @predibase
1/4 Blog: pbase.ai/introducing-RFT Webinar: pbase.ai/43WZv1g Playground: pbase.ai/3DR6WMP Open-Source PyTorch-to-Triton model: pbase.ai/4bHgDKw
The First Reinforcement Fine-Tuning Platform for LLMs
From rubrik.com
2.6K
Predibase by Rubrik
@predibase
Aug 4, 2023
Ready to operationalize LLMs? 🔌 Get best-in-class #RAG with privately hosted #opensource LLMs on managed infra right in your #VPC thanks to @predibase and @llama_index. • Check the docs: gpt-index.readthedocs.io/en/latest/exam… • Get the notebook: colab.research.google.com/drive/1ESVuNhB…
4.1K
Predibase by Rubrik
@predibase
Feb 20, 2024
Introducing #LoRA Land: 25 fine-tuned #mistral-7b models that outperform #gpt4 for specific tasks. You can prompt all of the fine-tuned #LLMs and compare their results to mistral-7b-instruct in real time! Check out LoRA Land: pbase.ai/3ORqcwa
GIF
1.4K
Predibase by Rubrik
@predibase
May 31, 2023
✨ Exciting news: today we launched our Free Trial and expanded support for #finetuning and #deploying #LLMs! But, most exciting is the expansion of our Series A led by @felicis! Get the free trial: predibase.com/free-trial/ Read the @TechCrunch article: techcrunch.com/2023/05/31/low…
6.2K
Predibase by Rubrik
@predibase
Aug 17, 2023
Predibase + @langchain: The easiest way to #finetune and productionize open-source #LLMs! 🎇 Our partnership brings production-grade workflows and managed infrastructure to teams that want to build on state-of-the-art open-source #models. Learn more: pbase.ai/3qxmAXd
2.4K
Predibase by Rubrik
@predibase
Mar 19, 2025
Replying to @predibase
3/4 Train a model to beat Wordle with RFT
00:00
1.7K
Predibase by Rubrik
@predibase
Mar 19, 2025
Replying to @predibase
2/4 Predibase Reinforcement Fine-Tuning platform walkthrough
00:00
1.8K
Predibase by Rubrik
@predibase
Mar 20, 2025
Yesterday we launched #Reinforcement Fine-Tuning! Use it to fine-tune open-source #LLMs to outperform commercial models with only a handful of labeled datarows. #RFT helps align models to your specific needs through reward-based learning. Curious what it looks like? Take a
00:00
503
Predibase by Rubrik
@predibase
Mar 5, 2024
Fine-tuning + structured generation = improved #JSON generation with #LLMs! 🔥 Check out our blog and benchmarks to learn how you can reliably output JSON with open-source frameworks #LoRAX and #Outlines, and Predibase. 👏
LoRAX + Outlines: Better JSON Extraction with LoRA
From rubrik.com
731
Predibase by Rubrik
@predibase
May 21, 2025
It was an honor working with @AndrewYNg and the @DeepLearningAI team to bring Reinforcement Fine-tuning (#RFT) to the masses with this free deep dive course! Now anyone can take a small open-source #LLM and turn it into a reasoning powerhouse tailored to their use case with as
Andrew Ng
@AndrewYNg
May 21, 2025
New Course: Reinforcement Fine-Tuning LLMs with GRPO! Learn to use reinforcement learning to improve your LLM performance in this short course, built in collaboration with @Predibase, and taught by @TravisAddair, its Co-Founder and CTO, and @grg_arnav, its Senior Engineer and
00:00
5.4K