You can now run Kimi K2.7 Code locally! ๐
We shrank the 1T model to 325GB (-48%) via Dynamic 2-bit where important layers are upcasted.
Run at >40 tok/s on 330GB RAM/VRAM setups.
Run full precision on 610 GB.
Guide: https://t.co/SXZJ3IHMpY
GGUF: https://t.co/2lpUx7u0r8
Bagian paling sulit dari software development (dan semua field engineering, pada dasarnya) dalam bahasa simplenya adalah:
โfinding and solving the most impactful problem within constraints and least amount of investmentโ
https://t.co/FEhhKZLRKR
Weโre releasing PaperBench, a benchmark evaluating the ability of AI agents to replicate state-of-the-art AI research, as part of our Preparedness Framework.
Agents must replicate top ICML 2024 papers, including understanding the paper, writing code, and executing experiments.
Although it's a late post, but
I've completed Advent of Code 2024 ๐๐.
I really enjoyed doing all the puzzles. Learned new concepts like observing patterns and graph clique, all while doing this in Rust
Merry Christmas and Happy New Year, everyone!
Everything you love about generative models โ now powered by real physics!
Announcing the Genesis project โ after a 24-month large-scale research collaboration involving over 20 research labs โ a generative physics engine able to generate 4D dynamical worlds powered by a physics simulation platform designed for general-purpose robotics and physical AI applications.
Genesis's physics engine is developed in pure Python, while being 10-80x faster than existing GPU-accelerated stacks like Isaac Gym and MJX. It delivers a simulation speed ~430,000 faster than in real-time, and takes only 26 seconds to train a robotic locomotion policy transferrable to the real world on a single RTX4090 (see tutorial: https://t.co/bEkIlCKqdf).
The Genesis physics engine and simulation platform is fully open source at https://t.co/DhBv7NdyqH. We'll gradually roll out access to our generative framework in the near future.
Genesis implements a unified simulation framework all from scratch, integrating a wide spectrum of state-of-the-art physics solvers, allowing simulation of the whole physical world in a virtual realm with the highest realism.
We aim to build a universal data engine that leverages an upper-level generative framework to autonomously create physical worlds, together with various modes of data, including environments, camera motions, robotic task proposals, reward functions, robot policies, character motions, fully interactive 3D scenes, open-world articulated assets, and more, aiming towards fullyย automated data generation for robotics, physical AI and other applications.
Open Source Code: https://t.co/DhBv7NdyqH
Project webpage: https://t.co/SBNyhFB0yn
Documentation: https://t.co/3yuBoaealV
1/n