iiinova — where your digital self keeps evolving

Reposted by Alex Dimakis

Kosta Derpanis @csprofkgd.bsky.social · 11/04/2025

Confirmed keynote speakers for the Greeks 🇬🇷 in #AI 2025 Symposium in Athens, Greece 🤗 @alexdimakis.bsky.social @manoliskellis.bsky.social www.greeksin.ai

0101

Alex Dimakis @alexdimakis.bsky.social · 13/04/2025

Excited to be part of Greeksin.ai

041

Alex Dimakis @alexdimakis.bsky.social · 03/04/2025

We are excited to release the OpenThinker2 reasoning models and data: 1. Outperforms DeepSeekR1-32B in reasoning. 2. Fully open source, open weights and open data (1M samples). 3. Post-trained only with SFT. RL post-training will likely further improve performance. github.com/open-thought...

github.com

GitHub - open-thoughts/open-thoughts: Fully open data curation for reasoning models

Fully open data curation for reasoning models. Contribute to open-thoughts/open-thoughts development by creating an account on GitHub.

0123

Alex Dimakis @alexdimakis.bsky.social · 12/02/2025

We are releasing OpenThinker-32B, the best 32B reasoning model with open data. We match or outperform Deepseek-R1-32B (a closed data model) in reasoning benchmarks. Congrats to Negin and the whole Open Thoughts team. github.com/open-thought...

Performance of the best known Reasoning models on various Benchmarks. OpenThinker-32B matches the current state of the art.

2258

Alex Dimakis @alexdimakis.bsky.social · 28/01/2025

What if we had the data that DeepSeek-R1 was post-trained on? We announce Open Thoughts, an effort to create such open reasoning datasets. Using our data we trained Open Thinker 7B an open data model with performance very close to DeepSeekR1-7B distill. (1/n)

191

Alex Dimakis @alexdimakis.bsky.social · 22/01/2025

We just did a crazy 48h sprint to create the best public reasoning dataset using Berkeley's Sky-T1, Curator and DeepSeek R1. We can get o1-Preview reasoning on a 32B model and 48x less data than Deepseek. t.co/WO5UV2LZQM

t.co

https://www.bespokelabs.ai/blog/bespoke-stratos-the-unreasonable-effectiveness-of-reasoning-distillation

162

Alex Dimakis @alexdimakis.bsky.social · 14/01/2025

The Berkeley Sky computing lab just trained a GPT-o1 level reasoning model, spending only $450 to create the instruction dataset. The data is 17K math and coding problems solved step by step. They created this dataset by prompting QwQ at $450 cost. Q: Impossible without distilling a bigger model?

171

Alex Dimakis @alexdimakis.bsky.social · 08/01/2025

AI monoliths vs Unix Philosophy: The case for small specialized AI models. Current thinking is that AGI is coming, and one gigantic model will be able to solve everything. Current Agents are mostly prompts on one big model and prompt engineering is used for executing complex processes. (1/n)

192

Reposted by Alex Dimakis

Atula Tejaswi @atutej.bsky.social · 09/12/2024

Missed out on #Swift tickets? No worries—swing by our #SVFT poster at #NeurIPS2024 and catch *real* headliners! 🎤💃🕺 📌Where: East Exhibit Hall A-C #2207, Poster Session 4 East ⏲️When: Thu 12 Dec, 4:30 PM - 7:30 PM PST #AI #MachineLearning #PEFT #NeurIPS24

192

Alex Dimakis @alexdimakis.bsky.social · 19/11/2024

hello friends, I heard there is a party here?

270