Expert Specialized Fine-Tuning

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

DeepSeek LLM: Let there be answers

MOSS-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

A curated list of open-source projects related to DeepSeek Coder

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

DeepSeek Coder: Let the Code Write Itself

一种任务级GPU算力分时调度的高性能深度学习训练平台

PyTorch implementations of deep reinforcement learning algorithms and environments

AI magics meet Infinite draw board.

The test of different distributed-training methods on High-Flyer AIHPC

FireFlyer Record file format, writer and reader for DL training samples.

CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP