TGINSIGHT SIMILAR POSTS
Source channel @githubtrending · Post #15539 · Mar 5
#python#agent#llm#llm_agent#llm_reasoning#machine_learning_systems#mlsys#reinforcement_learning#rl AReaL is a free, open-source system for fast asynchronous reinforcement learning to train large AI models in math, coding, search, and agents. It decouples generation and training for up to 2.77x speedup, stable performance, and easy setup on single or 1000+ GPUs with algorithms like GRPO/PPO. Install via git/pip, run examples like GSM8K math instantly. You benefit by building top AI agents affordably and quickly, reproducing results with shared data/models, saving time/money vs. slow synchronous tools. https://github.com/inclusionAI/AReaL
Search: #openpose
@The2ndDim · Post #1794 · 03/07/2023, 07:02 PM
#AI_Generated#StableDiffusion#ControlNet#OpenPose#vtuber#kohaku_nene Stable Diffusion 通过 ControlNet 基于 OpenPose 来产生指定动作姿势的图片的效果是真不错。 指定动作姿势是容易了，但调参本身还是很麻烦，尤其是指定动作姿势之后出现“人体炼成失败”的概率也增加了不少，要靠各种玄学微调才能修好。