willccbb / trlLinks
Train transformer language models with reinforcement learning.
☆19Updated 7 months ago
Alternatives and similar repositories for trl
Users that are interested in trl are comparing it to the libraries listed below
Sorting:
- ☆155Updated 5 months ago
- Train your own SOTA deductive reasoning model☆107Updated 7 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆77Updated 6 months ago
- Code to accompany the Universal Deep Research paper (https://arxiv.org/abs/2509.00244)☆441Updated last month
- LLM reads a paper and produce a working prototype☆57Updated 5 months ago
- An overview of GRPO & DeepSeek-R1 Training with Open Source GRPO Model Fine Tuning☆37Updated 4 months ago
- An Automatic Prompt Optimization Framework for Large Language Models☆123Updated 2 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 8 months ago
- The code repository of the paper: Competition and Attraction Improve Model Fusion☆159Updated last month
- Source code for the collaborative reasoner research project at Meta FAIR.☆102Updated 5 months ago
- ☆68Updated 4 months ago
- ☆61Updated 2 months ago
- ☆78Updated last week
- ☆56Updated 3 months ago
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆184Updated 7 months ago
- Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.☆53Updated 5 months ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆125Updated last month
- Source code of "How to Correctly do Semantic Backpropagation on Language-based Agentic Systems" 🤖☆75Updated 10 months ago
- accompanying material for sleep-time compute paper☆115Updated 5 months ago
- ☆95Updated 6 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
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- ☆83Updated 2 months ago
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆56Updated 5 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 8 months ago
- ☆135Updated 6 months ago
- CodeScientist: An automated scientific discovery system for code-based experiments☆295Updated 3 months ago
- Verifiers for LLM Reinforcement Learning☆75Updated last month
- ☆95Updated 2 weeks ago
- Analysis code for Neurips 2025 paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆52Updated 2 months ago