Skip to content
Awesomelist
Type at least 2 letters

Search entries, descriptions and list names. Press Esc to close.

Arrow keys move, Enter opensFull search page

Entry

slime

Appears in 5 awesome lists

LLM post-training framework for RL Scaling from THUDM. Supports SFT and RL training with multi-turn compilation feedback, powering projects like TritonForge for automated GPU kernel generation. Apache 2.0 licensed.

Open github.comthudm/slime

Found in these lists

When LLM Agents Meet Reinforcement Learning

Section: Base Framework · Tsinghua University (THUDM)

FreshScore 81

Awesome LLM Resources

Section: Agentic RL

FreshScore 87

Awesome local LLM

Section: Training and Fine-tuning · an LLM post-training framework for RL Scaling

FreshScore 87

Awesome Open Source AI

Section: 7. Training & Fine-tuning Ecosystem · LLM post-training framework for RL Scaling from THUDM. Supports SFT and RL training with multi-turn compilation feedback, powering projects like TritonForge for automated GPU kernel generation. Apache 2.0 licensed.

FreshScore 89

Awesome Production Machine Learning

Section: Industry Strength Reinforcement Learning · slime is an LLM post-training framework for RL Scaling.

FreshScore 92

TRL

Train transformer language models with reinforcement learning.

In 8 listsDetails

Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

In 5 listsDetails

OpenRLHF

an easy-to-use, high-performance open-source RLHF framework built on Ray, vLLM, ZeRO-3 and HuggingFace Transformers, designed to make RLHF training simple and accessible

In 4 listsDetails

RLinf

Scalable open-source RL infrastructure for post-training foundation models via reinforcement learning. Features M2Flow paradigm for embodied AI and agentic workflows with real-world robotics integrations. Apache 2.0 licensed.

In 3 lists

sentence-transformers

a Python library for using and training embedding and reranker models for applications like retrieval augmented generation, semantic search, and more

In 3 lists

heretic

Open-source system for automatic censorship and robustness suppression removal in language-model outputs.

In 3 lists

prime-rl

Agentic RL Training at Scale from Prime Intellect. Framework for large-scale reinforcement learning capable of scaling to 1000+ GPUs with fully asynchronous RL, FSDP2 training, and vLLM inference. Apache 2.0 licensed.

In 3 lists

veRL

Volcano Engine Reinforcement Learning for LLMs with PPO, GRPO, REINFORCE++, DAPO (EuroSys 2025).

In 3 lists