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"
  ☆556Updated last month
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆280Updated last month
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆248Updated 2 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆302Updated 2 weeks ago
• JinjieNi / MegaDLMs
  GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…
  ☆259Updated last week
• ZHZisZZ / dllm
  dLLM: Simple Diffusion Language Modeling
  ☆529Updated last week
• facebookresearch / PhysicsLM4
  Physics of Language Models, Part 4
  ☆255Updated 3 months ago
• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆304Updated last month
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆301Updated this week
• huggingface / picotron_tutorial
  ☆225Updated 3 weeks ago
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆210Updated 8 months ago
• thinking-machines-lab / batch_invariant_ops
  ☆894Updated 2 weeks ago
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆99Updated 8 months ago
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆355Updated 11 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆223Updated last week
• meta-pytorch / torchforge
  PyTorch-native post-training at scale
  ☆532Updated this week
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆192Updated 11 months ago
• kvfrans / lmpo
  ☆121Updated 2 weeks ago
• sustcsonglin / linear-attention-and-beyond-slides
  ☆96Updated 8 months ago
• microsoft / ArchScale
  Simple & Scalable Pretraining for Neural Architecture Research
  ☆299Updated 2 weeks ago
• marin-community / marin
  Open-source framework for the research and development of foundation models.
  ☆611Updated this week
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆300Updated 9 months ago
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆125Updated 6 months ago
• ypwang61 / One-Shot-RLVR
  [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example
  ☆375Updated last month
• dllm-reasoning / d1
  Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"
  ☆352Updated 4 months ago
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆367Updated 2 months ago
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆564Updated 2 weeks ago
• SakanaAI / RLT
  Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.
  ☆348Updated 4 months ago
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆450Updated 6 months ago
• s-sahoo / Eso-LMs
  Esoteric Language Models
  ☆106Updated last month