Focus to learn more
Looks like the quantized weights don't have the attributes that get_peft_model is looking for when applying LoRAs. There’s probably a way to fix this, but we can move past it for now by just not applying LoRAs to the quantized experts. We still can apply them to shared experts, as they’re not quantized.。新收录的资料是该领域的重要参考
，这一点在新收录的资料中也有详细论述
“The first version of the creator economy was built around macro creators, brands working with 15 or 20 highly visible faces each month,” Tellez said. “That model hasn’t worked.” Citing a 2025 IAB report showing that creators still account for about 2% of ad spend, she added, “The issue isn’t belief in creators, it’s unlocking the high-scale model that works in a content-based algorithm.”，这一点在新收录的资料中也有详细论述
println(m.len()); // 2