Find similar content

Source channel @githubtrending · Post #15340 · Dec 17

#python#gym#gym_environment#reinforcement_learning#reinforcement_learning_agent#reinforcement_learning_environments#rl_environment#rl_training NeMo Gym helps you build and run reinforcement‑learning training environments for large language models, letting you develop, test, and collect verified rollouts separately from the training loop and integrate with your preferred RL framework and model endpoints (OpenAI, vLLM, etc.). It includes ready resource servers, datasets, and patterns for multi‑step, multi‑turn, and tool‑using scenarios, runs on a typical dev machine (no GPU required), and is early-stage with evolving APIs and docs. Benefit: you can generate high‑quality, verifiable training data faster and plug it into existing training pipelines to improve model behavior. https://github.com/NVIDIA-NeMo/Gym

Hashtags

#python #gym #gym_environment #reinforcement_learning #reinforcement_learning_agent #reinforcement_learning_environments #rl_environment #rl_training

Results

1 similar post found

Search: #gopher

当前筛选 #gopher清除筛选

Libreware

@libreware · Post #1321 · 08/29/2024, 08:23 PM

Find similar View

__ __ _ __ / /_____ ____ / /_(_) /__ / __/ __ \/ __ \/ __/ / //_/ / /_/ /_/ / /_/ / /_/ / ,< \__/\____/\____/\__/_/_/|_| tootik v0.12.0 [https://github.com/dimkr/tootik] tootik is a federated nanoblogging service for the small internet. tootik allows people to participate in the fediverse using their Gemini, Gopher or Finger client of choice and makes the fediverse lighter, more private and more accessible. tootik's interface strips content to bare essentials (like text and links), puts the users in control of the content they see and tries to "slow down" the fediverse to make it more compatible with the slower pace of the small internet. It's a single executable that handles both the federation (using ActivityPub) and the frontend (using Gemini) aspects, while sqlite takes care of persistency. It should be lightweight and efficient enough to host a small community even on a cheap server, and hopefully, be easy to hack on. tootik implements only a small subset of ActivityPub, and probably doesn't really conform to the spec. Changelog: [https://github.com/dimkr/tootik/releases/tag/0.12.0] #Gemini#Gopher#Guppy#Fediverse#ActivityPub

Hashtags

#gemini #gopher #guppy #fediverse #activitypub