

It's crazy that a 4B model can match GPT-OSS-120B **even on knowledge benchs** like MMLU and GPQA! Knowledge was long a limitation of smol models ; not anymore. This 4B could be a good candidate for the "agentic core" model described by @karpathy

By
–


It's crazy that a 4B model can match GPT-OSS-120B **even on knowledge benchs** like MMLU and GPQA! Knowledge was long a limitation of smol models ; not anymore. This 4B could be a good candidate for the "agentic core" model described by @karpathy

By
–
I’ll believe it when I see it. So far I have not been impressed with any other model in LM studio aside from GPT OSS 120B.
By
–
QueryWeaver GitHub: (don't forget to star )
By
–
Volume 322 proceedings.mlr.press/v312 Proccedings of the AAAI Workshop on Audio-Centric AI Is now available on PMLR.
By
–
Great breakdown! One thing worth adding: temperature isn't just about creativity vs. determinism. It fundamentally reshapes the probability distribution over the entire vocabulary. A practical tip: instead of jumping straight to high temperature for 'creativity,' try
By
–
I mean @Albedo got approved to do 10cm gsd which with ml super res I already getting as powerful as high alt aerial

By
–
Build a Text-to-Image Generator (from Scratch), with transformers and diffusions: http://
amzn.to/3MFbyK4 by @mark_h_liu v/ @ManningBooks
By
–
I thought Grok was truth seeking, this is just plain old hallucinations
By
–
Good enough GSD to read license plates and facial id for sure – has been for a while – just limited to public sector; modulo albedo tho I have yet to see crispy 10cm imagery from them yet

By
–
See the latest book from @AltoValentina
, released by @PacktDataML at http://
amzn.to/4p98LYl "AI Agents in Practice — Design, Implement, and Scale Autonomous #AI Systems for Production" Book Description (from Amazon): As AI agents evolve to take on complex tasks and operate