mingyin0312 / RLFromScratchLinks
☆446Updated last month
Alternatives and similar repositories for RLFromScratch
Users that are interested in RLFromScratch are comparing it to the libraries listed below
Sorting:
- Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"☆538Updated 2 weeks ago
- rl from zero pretrain, can it be done? yes.☆277Updated 3 weeks ago
- Exploring Applications of GRPO☆248Updated 2 months ago
- ☆843Updated last week
- Tina: Tiny Reasoning Models via LoRA☆299Updated last month
- Physics of Language Models, Part 4☆250Updated 2 months ago
- An extension of the nanoGPT repository for training small MOE models.☆202Updated 7 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆300Updated 2 months ago
- ☆224Updated last week
- 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
- Normalized Transformer (nGPT)☆192Updated 11 months ago
- minimal GRPO implementation from scratch☆98Updated 7 months ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆260Updated last week
- ☆386Updated 10 months ago
- Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling☆448Updated 5 months ago
- ☆93Updated 8 months ago
- Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)☆484Updated last month
- Minimal hackable GRPO implementation☆294Updated 8 months ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆903Updated 7 months ago
- Open-source framework for the research and development of foundation models.☆532Updated this week
- [NeurIPS 2025] Reinforcement Learning for Reasoning in Large Language Models with One Training Example☆365Updated 2 weeks ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆539Updated this week
- Training teachers with reinforcement learning able to make LLMs learn how to reason for test time scaling.☆346Updated 4 months ago
- Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models☆220Updated last month
- Official Implementation for the paper "d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning"☆339Updated 3 months ago
- Post-training with Tinker☆1,096Updated last week
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆775Updated last week
- [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule☆331Updated last month
- A brief and partial summary of RLHF algorithms.☆132Updated 7 months ago
- A Gym for Agentic LLMs☆323Updated 2 weeks ago