Sinan Ozdemir

AI Education @FireworksAI_HQ 🔥 NLP + Gen AI Expert / LLM whisperer 🤖 AI Author 📚 Founder @Aikylie (acquired) 📈 Fellow @YCombinator

[Unsloth AI @UnslothAI]

GLM-5.2 can now be run locally!🔥

The 2-bit model retains ~82% accuracy after we shrunk it from 1.51TB to 238GB (-84% size).

Run on a 256GB Mac or RAM/VRAM setups.

GLM-5.2 is the strongest open model to date.

Guide: https://t.co/bI7FeeKHDd
GGUF: https://t.co/BMkxswdj5N

[Jeremy Howard @jeremyphoward]

BTW I've been using using @FireworksAI_HQ for inference. Other providers might not be as fast.

[Sinan Ozdemir @Prof_OZ]

POV your prompt engineering is simple yet powerful. Nice work! 🦾

[Jamari @hi_jamari]

I just doubled llama-405b's long context performance on this benchmark:

Same haystack & base prompt, but I added 3 examples that were VERY semantically similar to the real thing.

Result is 70 full accuracy hits, as opposed to the no-shot's 30.

Thanks to @Prof_OZ for the idea

[Sinan Ozdemir @Prof_OZ]

Thanks to everyone who came out!

[ODSC (Open Data Science Conference) AI @_odsc]

Quite the line for the book signing with @Prof_OZ !

[Sinan Ozdemir @Prof_OZ]

POV I didn't like your answer on my panel and it's time to defend your honor

[Sinan Ozdemir @Prof_OZ]

Asking @Google's Gemini and @openai's GPT-4 the exact same prompt tends to yield strangely similar responses which is always fascinating to me. I honestly wonder how this happens. Haven't tried with other large LLMs yet.

[Sinan Ozdemir @Prof_OZ]

@useintro It's hard to admit when a theory you had wasn't 100% right (especially ones in extremely public fields like AGI) but when you have the right people working on what they're good at on a unified goal, things can move fast!

[Sinan Ozdemir @Prof_OZ]

The joys of alignment 😂 and it didn't even write it in markdown after that

[Sinan Ozdemir @Prof_OZ]

🎙️ Out Now: "Practically Intelligent" E10 - Decoding AI Hype 🚀

Join us and @natolambert as we talk about how to stay accurately informed in AI. 🔍🤖

👉 Listen for tips on navigating the AI hype cycle! https://t.co/ve219gjURn

#AI #TechPodcast #MachineLearning #Innovation #LLM

[Sinan Ozdemir @Prof_OZ]

I had a blast chatting about LLMs on the latest episode of @_odsc's Ai X Podcast! 🎙️ Check it out! 🌟

[ODSC (Open Data Science Conference) AI @_odsc]

Dive into the Exciting World of Large Language Models with Sinan Ozdemir in the new episode of the ODSC’s Ai X Podcast! ️

Don't miss this opportunity to gain valuable knowledge from a leading expert @Prof_OZ
Listen now on your favorite podcast platform: https://t.co/tZoviP9Wor

[Intro @intro]

"Get as far as you can without raising a single dollar." - Sophia Amoruso's advice for startup founders:

--
Found this valuable? Repost and follow @useintro to learn how the world's most successful entrepreneurs built $100M+ businesses.

[Sinan Ozdemir @Prof_OZ]

🌟🎙️ "Practically Intelligent" E9 is out! 🚀 Join us as we dissect Coatue's AI report and debunk some myths in AI while exploring 2023 trends & what's next in 2024! 📆🤖

🎧 Listen here: https://t.co/QZ1yR1vQkp

#AI #TechTrends #OpenSource #DataScience #Podcast #Innovation

[Sinan Ozdemir @Prof_OZ]

🌟Practically Intelligent Ep 8 is out!🚀 Join Akshay & me as we dive into multimodal AI with @JacobSolawetz talking vision transformers, research trends & more! #AI #MultimodalAI #TechPodcast

🔗 https://t.co/7KR5pcGtK3

#ComputerVision #LanguageModels #Innovation #TechInsights

[Sinan Ozdemir @Prof_OZ]

🚀 My new post on #AIAlignment is out today!

📊 AI vs. Human rating: lots of stark differences
💡 Key takeaways: scoring mismatch, & positional bias
🔍 Check it out : https://t.co/HcVNB4kbdc

🗣️ Share your thoughts on #AI's future!

#MachineLearning #DataScience #OReilly

[Sinan Ozdemir @Prof_OZ]

Looks like I’m on sale, and just in time to give someone a very special someone a very specific gift for the holidays 🎁

[InformIT @InformIT]

Quick start guides to AI and LLMs, technologies quickly shaping our present and future by @Prof_OZ.

Use direct-to-cart link and save 60%: https://t.co/dIIre0boI8

#ai #llm #datascience #python #gpt

[Sinan Ozdemir @Prof_OZ]

🚀 Shared my insights/resources on Open-Source LLMs at IBM WatsonX's TechXchange today.

Highlights: 👥 Collaboration in open-source 🔧 Optimizing model efficiency 📊 Importance of quality data & labeling in AI

🔗 Slides & Colab: https://t.co/clv1hBKbEw
#LLMs #AI #ML

[Sinan Ozdemir @Prof_OZ]

🚀#PracticallyIntelligent Ep 7 is out! 🎧 Join us and @heuristicity for a deep dive into #AI Benchmarking. We explore benchmarks in AI progress 📈 and the fine line between conceptual & rote learning in AI 🎓
👉 Listen now: https://t.co/Rt5HMCedgq
#MachineLearning #LLMs

[Sinan Ozdemir @Prof_OZ]

🚀 New intro LLM post: Fine-Tune LLaMA 2! Check out my Colab notebook for efficient LLM instruction fine-tuning with LoRA & Quantization.

🔥 Streamlined coding, query understanding enhancements, precise learning methods.

👉 https://t.co/46kR5oSB1k #LLaMA2 #AI #DataScience

[Sinan Ozdemir @Prof_OZ]

Thank you @_odsc west for having me and thank you to this packed room of eager learners for being amazing! #llm #opensource #alignment

[Sinan Ozdemir @Prof_OZ]

Prepping for my #ODSC alignment workshop next week and my TA/cat is watching for bugs in my #RLHF code