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"
  ☆569Updated 2 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆327Updated last month
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆282Updated 3 months ago
• facebookresearch / PhysicsLM4
  Physics of Language Models, Part 4
  ☆280Updated 2 weeks ago
• thinking-machines-lab / batch_invariant_ops
  ☆941Updated last month
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆219Updated 9 months ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆250Updated 4 months ago
• huggingface / picotron_tutorial
  ☆225Updated last month
• JinjieNi / MegaDLMs
  GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…
  ☆306Updated last month
• radixark / miles
  ☆629Updated this week
• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆310Updated 3 months ago
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆340Updated this week
• open-tinker / OpenTinker
  OpenTinker is an RL-as-a-Service infrastructure for foundation models
  ☆229Updated this week
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆138Updated 7 months ago
• marin-community / marin
  Open-source framework for the research and development of foundation models.
  ☆673Updated last week
• stanford-cs336 / spring2024-lectures
  ☆403Updated last year
• meta-pytorch / torchforge
  PyTorch-native post-training at scale
  ☆572Updated last week
• microsoft / ArchScale
  Simple & Scalable Pretraining for Neural Architecture Research
  ☆305Updated 3 weeks ago
• ZHZisZZ / dllm
  dLLM: Simple Diffusion Language Modeling
  ☆1,504Updated this week
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆584Updated this week
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆194Updated last year
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆100Updated 9 months ago
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆409Updated this week
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆465Updated 7 months ago
• microsoft / dion
  Dion optimizer algorithm
  ☆409Updated this week
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆404Updated 3 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…
  ☆362Updated last year
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆226Updated last month
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆306Updated 10 months ago
• openai / circuit_sparsity
  Open-source release accompanying Gao et al. 2025
  ☆471Updated 2 weeks ago