跳到正文
Aravind Srinivas· @AravSrinivas · X·· 3 小时前AI 评分57
AI 导读

Perplexity 开源两款决策模型:pplx-decider-flash-v1.2 为 4B 参数、每百万 token 1 美分,是 HF Decision Index 上的第一 4B 模型;pplx-decider-v1.2 为 27B 参数、每百万 token 2 美分,总榜第二。两者通过 Perplexity Decisions API 和 Hugging Face 开放权重提供,文本与视觉成绩提升,一次前向传播可并行处理请求中的所有问题,推理最快提升至 5 倍。

正文

We just open-sourced another pair of state-of-the-art Decision Models:

pplx-decider-flash-v1.2: 4B params, 1 cent per million tokens (top 4B model on HF Decision Index)

pplx-decider-v1.2: 27B params, 2 cents per million tokens (#2 on HF Decision Index overall - for now, will improve rapidly)

Both are available on the Perplexity Decisions API as well as in the form of open weights on @huggingface

Enjoy!

引用Perplexity Developers@perplexitydevs
Our next generation of open weights multimodal decision models comes in two sizes, pplx-decider-v1.2 and pplx-decider-flash-v1.2. Text and vision scores improve. Inference is up to 5x faster: all questions in a request run in one pass. Flash is the top 4B on the Decision Index.
在 X 查看被引用的帖子

来源:Aravind Srinivas · x.com