Parameter-efficient Fine-tuning of LLMs with LoRA
49:45
LLM prompting optimization: Automatic Multi-step Reasoning and Tool Use
39:42
Mixture of Experts: Mixtral 8x7B
17:07
LoRA explained (and a bit about precision and quantization)
50:25
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs
45:11
LLM inference optimization: Model Quantization and Distillation
44:06
LLM inference optimization: Architecture, KV cache and Flash attention
20:03
Hakim, mahkemede gençle dalga geçiyor, ancak sonradan onun bir hukuk dahisi olduğunu keşfediyor!
48:07