minosvasilias / simple_grpoLinks
Simple GRPO scripts and configurations.
☆59Updated 8 months ago
Alternatives and similar repositories for simple_grpo
Users that are interested in simple_grpo are comparing it to the libraries listed below
Sorting:
- ☆55Updated 11 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆58Updated last week
- Project code for training LLMs to write better unit tests + code☆21Updated 5 months ago
- ☆88Updated last year
- Train your own SOTA deductive reasoning model☆108Updated 7 months ago
- ☆49Updated 8 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆61Updated this week
- Simple repository for training small reasoning models☆43Updated 8 months ago
- Official repo for Learning to Reason for Long-Form Story Generation☆72Updated 6 months ago
- ☆40Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 9 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆145Updated 8 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆35Updated last year
- An introduction to LLM Sampling☆79Updated 10 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆57Updated 5 months ago
- Learning to Retrieve by Trying - Source code for Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrieval☆51Updated 11 months ago
- ☆48Updated last year
- ☆46Updated 2 years ago
- Collection of autoregressive model implementation☆86Updated 6 months ago
- look how they massacred my boy☆63Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- Mixing Language Models with Self-Verification and Meta-Verification☆109Updated 10 months ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated 2 years ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆68Updated last year
- Score LLM pretraining data with classifiers☆54Updated last year
- Just a bunch of benchmark logs for different LLMs☆118Updated last year
- ☆68Updated 5 months ago
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆39Updated 6 months ago
- Verifiers for LLM Reinforcement Learning☆76Updated 6 months ago
- various experiments for scaling inference time compute with small reasoning models☆17Updated 9 months ago