Lists (3)
Stars
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
🔥 Clone and recreate any website as a modern React app in seconds
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
slime is an LLM post-training framework for RL Scaling.
Revisiting Mid-training in the Era of Reinforcement Learning Scaling
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval
Our library for RL environments + evals
[ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
Implementing DeepSeek R1's GRPO algorithm from scratch
[ICLR 2025] Train Small, Infer Large: Memory-Efficient LoRA Training for Large Language Models
MoBA: Mixture of Block Attention for Long-Context LLMs
Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
a minimal cache manager for PagedAttention, on top of llama3.
Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
[ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training
A Self-adaptation Framework🐙 that adapts LLMs for unseen tasks in real-time!
Training Large Language Model to Reason in a Continuous Latent Space