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"
  ☆576Updated 3 months ago
• changjonathanc / flex-nano-vllm
  FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
  ☆328Updated 2 months ago
• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆314Updated 3 months ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆252Updated 4 months ago
• huggingface / picotron_tutorial
  ☆224Updated last month
• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆225Updated 10 months ago
• Wenyueh / MinivLLM
  Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation
  ☆184Updated this week
• JinjieNi / MegaDLMs
  GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 tr…
  ☆312Updated 2 months ago
• tokenbender / avataRL
  rl from zero pretrain, can it be done? yes.
  ☆286Updated 3 months ago
• facebookresearch / PhysicsLM4
  Physics of Language Models, Part 4
  ☆303Updated last week
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆140Updated 8 months ago
• thinking-machines-lab / batch_invariant_ops
  ☆949Updated 2 months ago
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆346Updated 3 weeks ago
• test-time-training / e2e
  Official JAX implementation of End-to-End Test-Time Training for Long Context
  ☆297Updated 2 weeks ago
• facebookresearch / memory
  Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, spars…
  ☆370Updated last year
• radixark / miles
  Miles is an enterprise-facing reinforcement learning framework for large-scale MoE post-training and production workloads, forked from an…
  ☆714Updated this week
• fangyuan-ksgk / Tiny-GRPO
  minimal GRPO implementation from scratch
  ☆102Updated 10 months ago
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆421Updated 4 months ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆225Updated 7 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆195Updated last year
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.
  ☆614Updated last week
• microsoft / dion
  Dion optimizer algorithm
  ☆416Updated last week
• meta-pytorch / torchforge
  PyTorch-native post-training at scale
  ☆585Updated last week
• axon-rl / gem
  A Gym for Agentic LLMs
  ☆420Updated 2 weeks ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆226Updated 2 months ago
• microsoft / ArchScale
  Simple & Scalable Pretraining for Neural Architecture Research
  ☆306Updated last month
• open-thought / tiny-grpo
  Minimal hackable GRPO implementation
  ☆315Updated 11 months ago
• dllm-reasoning / d1
  Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"
  ☆393Updated 3 weeks ago
• yihedeng9 / rlhf-summary-notes
  A brief and partial summary of RLHF algorithms.
  ☆142Updated 10 months ago
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆198Updated last month