Llama3 Leaps Ahead with Data Alone
·78 words·1 min
Blog
Pretraining has Gotten 10x Faster in Past Year!
·43 words·1 min
Great Papers
·53 words·1 min
Marvels of ENIAC
·486 words·3 mins
Intelligence and FLOPs Efficiency
·141 words·1 min
CIFAR-10 Training to 94% Accuracy in 3.29s
·48 words·1 min
Matmul on CPUs
·47 words·1 min
Using rusage
·53 words·1 min
When Uniform Isn't Uniform: A Bug Hunt Tale
·53 words·1 min
GPT-4 Training Time
·83 words·1 min