Sensitive content

This media may contain sensitive content.

Загрузка видео...

Не удалось загрузить видео

На главную

We can celebrate Halloween any time! Especially when BIG WEREWOLF Transformations are involved! Part 1. Artist: SilverBulletProof Video & Audio: BigHouseOfLove Voice: Me #transform #werewolf #werewolftf #transformation #comicdub #nsfw

15,328 просмотров • 8 месяцев назад •via X (Twitter)

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Putin addresses Armenian PM Nikol Pashinyan’s complaint that the Moscow-led CSTO military alliance failed to support Armenia during Azerbaijan’s retaking of Karabakh: "Now, on security, that’s obviously the most sensitive issue right now. We understand that. We talk about it a lot, especially when it comes to Karabakh. We know you and your colleagues have had, and still have, questions and complaints about the CSTO. We keep coming back to it. "But after Prague in 2022, when you recognised Karabakh as part of Azerbaijan, any CSTO involvement would have meant stepping into what had effectively become an internal Azerbaijani issue. That just wouldn’t have been appropriate. "As for Karabakh being reintegrated into Azerbaijan, I’m not judging whether that’s good or bad. But from the point of view of restoring normal life, that was probably part of the thinking. "And now, thanks to your efforts and those of the Azerbaijani president, it looks like things are starting to stabilise. The US president was also involved. You can see some movement, transport links reopening, things slowly getting back on track. "The key now is to keep building on that and find ways to strengthen relations further. Maybe it would be better if we didn’t have to draw lines under these issues, but that’s part of politics, especially during election campaigns. "And finally, we have a lot of friends in Armenia. A lot. We know that."

Brian McDonald

18,687 просмотров • 6 месяцев назад

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...

kwindla

331,698 просмотров • 1 месяц назад