PulseAugur
EN
LIVE 15:47:25

Kimi K2 model boasts 1T parameters and SOTA HLE, while Soumith Chintala departs PyTorch

By PulseAugur Editorial · [1 sources] ·

Kimi K2, a new model from Kimi, boasts 1 trillion parameters and achieves state-of-the-art results on the HLE benchmark. It also demonstrates capabilities in BrowseComp and TauBench. Separately, Soumith Chintala has departed from PyTorch. AI

IMPACT Sets new SOTA on HLE benchmark, potentially influencing future model development.

RANK_REASON New model release with significant parameter count and benchmark performance.

Read on Smol AINews →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Kimi K2 model boasts 1T parameters and SOTA HLE, while Soumith Chintala departs PyTorch

COVERAGE [1]

  1. Smol AINews TIER_1 English(EN) ·

    Kimi K2 Thinking: 1T-A32B params, SOTA HLE, BrowseComp, TauBench && Soumith leaves Pytorch

    **Moonshot AI** launched **Kimi K2 Thinking**, a **1 trillion parameter** mixture-of-experts (MoE) model with **32 billion active experts**, a **256K context window**, and native **INT4 quantization-aware training**. It achieves state-of-the-art results on benchmarks like **HLE (…

RELATED ENTITIES

RELATED TOPICS