Improvement Technique

Hierarchal Agent Loop Optimizer HALO is an RLM-based agent optimization technique capable of recursively self-improving agents by analyzing their execution traces and suggesting changes. This work is inspired by the Mismanaged Genius Hypothesis

A walkthrough of using the bootstrap fewshot and GEPA optimizers in DSPy

Agentic systems often reach a plateau after proof-of-concept because they depend on humans to diagnose edge cases and correct failures. T...

Understanding GRPO and New Insights from Reasoning Model Papers

Discover the key differences between RAG and fine-tuning, what each approach can bring, and how to choose the right AI approach for your business goals.

Learn all about Reinforcement Learning (RL) and how to train your own DeepSeek-R1 reasoning model with Unsloth using GRPO. A complete guide from beginner to advanced.

➤ Check out our updated Reinforcement Learning guide!

After completing our multi-turn tokenization and masking refactoring, we eliminated a critical bottleneck that was preventing us from building a more consistent and flexible rollout system for our Agent RL research. This breakthrough enabled us to implement a LangGraph-based rollout for VeRL in just a few days, which we’ve already successfully deployed in our Agent RL experiments. In this article, I’ll share our journey from VeRL’s native multi-turn implementation to our new LangGraph-based solution, explaining both the motivations driving this evolution and the technical details of our implementation.

A Blog post by Sara Han Díaz on Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

A deep dive into the methods, fine-tuning pipeline, and operational risks of building specialised models.

Best practices for LoRA hyperparameters and how they affect the fine-tuning process.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Step-by-step guide to fine-tuning the Mistral reasoning model on a medical MCQs dataset using the Transformers framework.

AI Engineering bootcamp. Contribute to apatti/AIEBootcamp development by creating an account on GitHub.

but wtf not? - skill gap - high fine-tuning costs - lack of standards and unified approaches over the past few weeks I've been working on maestro - streamlined tool for VLM fine-tuning link: — SkalskiP (@skalskip92)

In this video, we show you how to fine-tune DeepSeek R1, an open-source reasoning model, using LoRA (Low-Rank Adaptation). We'll also be using Kaggle, Hugging Face and Weights & Biases. We walk you through data preparation, model configuration, and optimization, including advanced techniques like four-bit quantization for efficient training on consumer GPUs. By the end of this tutorial, you’ll be equipped with the skills to customize DeepSeek R1 for your own specialized tasks, such as medical reasoning. 🔗 Resources & Tutorials Kaggle Notebook: https://www.kaggle.com/code/aan1994/fine-tuning-deepseek-r1-reasoning-model-youtube How Transformers Work: https://www.datacamp.com/tutorial/how-transformers-work Fine-Tuning DeepSeek R1 Reasoning Model: https://www.datacamp.com/tutorial/fine-tuning-deepseek-r1-reasoning-model DeepSeek R1 Blog Overview: https://www.datacamp.com/blog/deepseek-r1 Understanding Janus Pro: https://www.datacamp.com/blog/janus-pro DeepSeek R1 Project Walkthrough: https://www.datacamp.com/tutorial/deepseek-r1-project DeepSeek vs ChatGPT: https://www.datacamp.com/blog/deepseek-vs-chatgpt Qwen-2.5 MAX Model: https://www.datacamp.com/blog/qwen-2-5-max DeepSeek R1 Ollama Tutorial: https://www.datacamp.com/tutorial/deepseek-r1-ollama 📕 Chapters 00:00 Introduction 00:30 Why Fine-Tuning DeepSeek Matters 02:30 LoRA Explained with a PS5 Factory Analogy 05:20 Tools & Setup Overview 09:00 Loading DeepSeek R1 Model and Tokenizer 16:10 Formatting Data for Fine-Tuning 23:00 Applying LoRA for Efficient Updates 34:00 Configuring Training Parameters 43:15 Running the Fine-Tuning Process on Kaggle 46:00 Comparing Model Performance After Fine-Tuning 47:50 Final Thoughts on Future Models 📱 Follow Us on Social Media Facebook: https://www.facebook.com/datacampinc/ Twitter: https://twitter.com/datacamp LinkedIn: https://www.linkedin.com/school/datacampinc/ Instagram: https://www.instagram.com/datacamp/ #deepseek #DeepSeekR1 #FineTuningAI #LearnAI #MachineLearning #Transformers #HuggingFace #Kaggle #WeightsAndBiases #LoRA #LargeLanguageModels #DeepSeekTutorial #AIResearch #AIOptimization #DataScience

Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer. - transformerlab/transformerlab-app

I summarise the kinds of evaluations that are needed for a structured data generation task.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.