mingyin0312 / RL4LLMLinks
RL significantly the reasoning capability of Qwen2.5-1.5B-Instruct
☆30Updated 8 months ago
Alternatives and similar repositories for RL4LLM
Users that are interested in RL4LLM are comparing it to the libraries listed below
Sorting:
- ☆48Updated last year
- nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)☆121Updated 5 months ago
- minimal GRPO implementation from scratch☆98Updated 7 months ago
- Simple GRPO scripts and configurations.☆59Updated 8 months ago
- Collection of autoregressive model implementation☆86Updated 6 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆103Updated 2 weeks ago
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆101Updated last month
- Simple repository for training small reasoning models☆43Updated 8 months ago
- Verifiers for LLM Reinforcement Learning☆76Updated 6 months ago
- Tina: Tiny Reasoning Models via LoRA☆299Updated last month
- An extension of the nanoGPT repository for training small MOE models.☆202Updated 7 months ago
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆240Updated 11 months ago
- Exploring Applications of GRPO☆248Updated 2 months ago
- My fork os allen AI's OLMo for educational purposes.☆30Updated 10 months ago
- A Qwen .5B reasoning model trained on OpenR1-Math-220k☆14Updated 2 weeks ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆59Updated last week
- A pipeline for LLM knowledge distillation☆109Updated 6 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆72Updated 6 months ago
- ☆88Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 9 months ago
- A simplified implementation for experimenting with RLVR on GSM8K, This repository provides a starting point for exploring reasoning.☆136Updated 8 months ago
- ☆67Updated last year
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆108Updated 4 months ago
- ☆52Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- ☆46Updated 6 months ago
- Code for NeurIPS LLM Efficiency Challenge☆59Updated last year
- Unofficial implementation of https://arxiv.org/pdf/2407.14679☆49Updated last year
- ☆122Updated 8 months ago
- FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.☆296Updated 2 months ago