Alternatives and similar repositories for Tiny-GRPO:

Users that are interested in Tiny-GRPO are comparing it to the libraries listed below

• wolfecameron / nanoMoE
  An extension of the nanoGPT repository for training small MOE models.
  ☆138Updated 2 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆172Updated 3 months ago
• joey00072 / nanoGRPO
  nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)
  ☆103Updated 3 weeks ago
• huggingface / picotron_tutorial
  ☆181Updated 2 months ago
• Mohammadjafari80 / GSM8K-RLVR
  A simplified implementation for experimenting with Reinforcement Learning (RL) on GSM8K, inspired by RLVR and Deepseek R1. This repositor…
  ☆84Updated 3 months ago
• lucidrains / coconut-pytorch
  Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
  ☆165Updated 4 months ago
• melisa-writer / short-transformers
  Prune transformer layers
  ☆69Updated 11 months ago
• brendanhogan / DeepSeekRL-Extended
  Exploring Applications of GRPO
  ☆189Updated this week
• facebookresearch / ReasonIR
  Official repository for paper "ReasonIR Training Retrievers for Reasoning Tasks".
  ☆112Updated last week
• SeunghyunSEO / optimized_hf_llama_class_for_training
  ☆47Updated 8 months ago
• itsnamgyu / block-transformer
  Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)
  ☆153Updated 3 weeks ago
• sanyalsunny111 / LLM-Inheritune
  This is the official repository for Inheritune.
  ☆111Updated 2 months ago
• shangshang-wang / Tina
  Tina: Tiny Reasoning Models via LoRA
  ☆164Updated 2 weeks ago
• TIGER-AI-Lab / CritiqueFineTuning
  Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate"
  ☆141Updated 2 weeks ago
• LLM360 / k2-train
  ☆50Updated 11 months ago
• allenai / OLMo-core
  PyTorch building blocks for the OLMo ecosystem
  ☆205Updated this week
• THU-KEG / Agentic-Reward-Modeling
  Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
  ☆90Updated 2 months ago
• mingyin0312 / RL4LLM
  RL significantly the reasoning capability of Qwen2.5-1.5B-Instruct
  ☆28Updated 2 months ago
• hao-ai-lab / Dynasor
  Simple extension on vLLM to help you speed up reasoning model without training.
  ☆148Updated this week
• OpenPipe / deductive-reasoning
  Train your own SOTA deductive reasoning model
  ☆91Updated 2 months ago
• jeffreysijuntan / lloco
  The official repo for "LLoCo: Learning Long Contexts Offline"
  ☆116Updated 10 months ago
• ServiceNow / PipelineRL
  A scalable asynchronous reinforcement learning implementation with in-flight weight updates.
  ☆100Updated this week
• ScalingIntelligence / large_language_monkeys
  ☆92Updated 7 months ago
• facebookresearch / RAM
  A framework to study AI models in Reasoning, Alignment, and use of Memory (RAM).
  ☆226Updated this week
• fangyuan-ksgk / Evolutionary-Model-Merge
  Unofficial Implementation of Evolutionary Model Merging
  ☆38Updated last year
• tyler-romero / microR1
  Simple repository for training small reasoning models
  ☆27Updated 3 months ago
• alperiox / Compact-Language-Models-via-Pruning-and-Knowledge-Distillation
  Unofficial implementation of https://arxiv.org/pdf/2407.14679
  ☆44Updated 8 months ago
• ypwang61 / One-Shot-RLVR
  official repository for “Reinforcement Learning for Reasoning in Large Language Models with One Training Example”
  ☆118Updated this week
• sail-sg / oat
  🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.
  ☆338Updated this week
• wuhy68 / Parameter-Efficient-MoE
  Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks
  ☆143Updated 7 months ago