Alternatives and similar repositories for RLFromScratch

Users that are interested in RLFromScratch are comparing it to the libraries listed below

• McGill-NLP / nano-aha-moment
  Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"
  ☆538Updated 2 weeks ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆277Updated 3 weeks ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆248Updated 2 months ago
• thinking-machines-lab / batch_invariant_ops
  ☆843Updated last week
• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆299Updated last month
• facebookresearch / PhysicsLM4
  Physics of Language Models, Part 4
  ☆250Updated 2 months ago
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆202Updated 7 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆300Updated 2 months ago
• huggingface / picotron_tutorial
  ☆224Updated last week
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆342Updated 10 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆192Updated 11 months ago
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆98Updated 7 months ago
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆260Updated last week
• stanford-cs336 / spring2024-lectures
  ☆386Updated 10 months ago
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆448Updated 5 months ago
• sustcsonglin / linear-attention-and-beyond-slides
  ☆93Updated 8 months ago
• raymin0223 / mixture_of_recursions
  Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)
  ☆484Updated last month
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆294Updated 8 months ago
• fla-org / native-sparse-attention
  🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
  ☆903Updated 7 months ago
• marin-community / marin
  Open-source framework for the research and development of foundation models.
  ☆532Updated this week
• ypwang61 / One-Shot-RLVR
  [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example
  ☆365Updated 2 weeks ago
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆539Updated this week
• SakanaAI / RLT
  Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
  ☆346Updated 4 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆220Updated last month
• dllm-reasoning / d1
  Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"
  ☆339Updated 3 months ago
• thinking-machines-lab / tinker-cookbook
  Post-training with Tinker
  ☆1,096Updated last week
• MoonshotAI / checkpoint-engine
  Checkpoint-engine is a simple middleware to update model weights in LLM inference engines
  ☆775Updated last week
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆331Updated last month
• yihedeng9 / rlhf-summary-notes
  A brief and partial summary of RLHF algorithms.
  ☆132Updated 7 months ago
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆323Updated 2 weeks ago