OPEN SOURCE - AI Dynamics

This is amaaaazing! This must be the best way to get started with GPU programming now

Literally, as you type each char, it creates and runs GPU in real time, runs it, and reports the results.🤯

I didn't expect to see a FastHTML/gpu.cpp cross-over… let alone something so cool. https://t.co/LzVHuDltlt
— Jeremy Howard (@jeremyphoward) 13 septembre 2024

This is amaaaazing! This must be the best way to get started with GPU programming now Literally, as you type each char, it creates and runs GPU in real time, runs it, and reports the results. I didn't expect to see a FastHTML/gpu.cpp cross-over… let alone something so cool.

→ View original post on X — @jeremyphoward

13 September 2024

TurboLoRA: Boosting LLM Inference Throughput with Parameter-Efficient Fine-Tuning

By

@predibase

–

13 September 2024 22h09

Want to supercharge your #LLM inference? Traditional fine-tuning methods make it possible to achieve #GPT4 level accuracy with small open-source models (#SLMs). But, what about throughput? Introducing #TurboLoRA, a new parameter-efficient fine-tuning method that increases

→ View original post on X — @predibase

13 September 2024

Adapting Meditron Medical AI Model for Cancer Research

By

@jessyseonoob

–

13 September 2024 18h33

bon bah du coup c'est possible d'1dapter ce qu'ils ont fait avec meditron chez meta pour l'adapter sur mistral ai ? j'ai mon fils de 10 ans qui a un cancer, donc si je peux aider les médecins a faire de la recherche et avoir des réponses les moins biaisées. #medicbrain

→ Voir le post original sur X — @jessyseonoob

13 September 2024