trl
Here are 41 public repositories matching this topic...
Language: All
Sort: Most stars
Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach
-
Updated
Jan 15, 2024 - Python
An implementation of GRPO for Unsloth's VLMs training
-
Updated
Aug 7, 2025 - Python
Code repository dedicated to experimenting and research with tiny reasoning language model
-
Updated
Nov 24, 2025 - Python
Various training, inference and validation code and results related to Open LLM's that were pretrained (full or partially) on the Dutch language.
-
Updated
Apr 9, 2024 - Jupyter Notebook
simpleR1: A Simple Framework for Training R1-like Models
-
Updated
Aug 12, 2025 - Python
使用trl、peft、transformers等库,实现对huggingface上模型的微调。
-
Updated
Mar 21, 2025 - Python
This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.
-
Updated
Apr 7, 2025 - Jupyter Notebook
Different post-training techniques for LLMs, including: SFT, DPO and Online RL
-
Updated
Sep 5, 2025 - Python
Notebooks to create an instruction following version of Microsoft's Phi 2 LLM with Supervised Fine Tuning and Direct Preference Optimization (DPO)
-
Updated
Nov 27, 2024 - Jupyter Notebook
Minimal code to train reasoning model with reinforcement learning.
-
Updated
Aug 9, 2025 - Python
Federated Supervised Fine-Tuning for Small Language Models (SLMs)
-
Updated
Sep 13, 2025 - Python
The overall aim of this project is to create a term rewriting system that could be useful in everyday programming, and to represent data in a way that roughly correspond to the definition of a term in formal logic. Terms should be familiar to any programmer because they are basically constants, variables, and function symbols.
-
Updated
Dec 16, 2020 - C#
Supervised Fine tuning using TRL library
-
Updated
Jan 24, 2024 - Jupyter Notebook
finetune gpt-oss and smollm3 on your data easily and cheaply
-
Updated
Aug 12, 2025 - Python
End-to-end implementation of Reinforcement Learning with Human Feedback (RLHF) to align a GPT-2 model with human preferences — covering Supervised Fine-Tuning (SFT), Reward Modeling, and PPO-based alignment — built from scratch in Python.
-
Updated
Sep 25, 2025 - Jupyter Notebook
This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.
-
Updated
Dec 31, 2025 - Jupyter Notebook
Direct Preference Optimization of ChatGPT2 using TRL Library
-
Updated
Jan 24, 2024 - Jupyter Notebook
Improve this page
Add a description, image, and links to the trl topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the trl topic, visit your repo's landing page and select "manage topics."