LLM Judges Prefers Fluff?
·47 words·1 min
Twitter Post
Announcement: Phi-3 14B Rivaling Llama3 70B
·28 words·1 min
Power of Inference Scaling
·51 words·1 min
Sample Efficiency
·46 words·1 min
Pretraining has Gotten 10x Faster in Past Year!
·43 words·1 min
Great Papers
·53 words·1 min
CIFAR-10 Training to 94% Accuracy in 3.29s
·48 words·1 min
Matmul on CPUs
·47 words·1 min
Scarce to Plentiful
·16 words·1 min
A Lifetime in 1T Tokens
·32 words·1 min