Fine-tuning LLMs
Fine-tune open-source LLMs with LoRA/QLoRA for custom tasks and domain adaptation.
0%
Confidence · no data yet
After this skill you can…
- Prepare fine-tuning datasets
- Run LoRA/QLoRA training with Unsloth or HF Trainer
- Evaluate and merge adapters
- Push models to Hugging Face Hub
Prerequisites
Watch (10 videos)
EigenTrace Large Language Model RLHF Analyzer Live Stream on Current Events
→ Fine-tune LLMs for specific tasks→ Use RLHF for LLM fine-tuning→ Optimize LLM performance
How are large language models trained?
→ Apply supervised fine-tuning to refine a large language model→ Use reinforcement learning to improve a large language model
Building an MLX Filler Word Detector #Shorts
→ Fine-tune a pre-trained model→ Optimize model performance for specific tasks
I Let AI Trade Fibonacci for 6 Years…
→ Optimize trading strategy parameters→ Improve trading strategy performance
Make LLMs Fly: Accelerating Bielik With NVIDIA Minitron and Data Curator
→ Fine-tune LLMs for specific languages→ Optimize LLMs for local languages
Model Optimization in Microsoft Foundry: Supervised Fine-Tuning
→ Apply Supervised Fine-Tuning→ Use Fine-Tuning for Specific Tasks→ Reduce Token Usage
What is Reinforcement Learning from Human Feedback (RLHF)
→ Fine-tune large language models using RLHF→ Adjust AI behavior based on human feedback
LLM Fine-Tuning 18: Unsloth Full Guide | Fine-Tune LLMs 2× to 4x Faster with Lowest GPU Memory
→ Train LLMs 2-4x faster→ Reduce GPU memory usage→ Use Unsloth for fine-tuning
LLM Fine-Tuning 17: Fine-Tune ANY LLM with LLaMA Factory | Full Guide (WebUI + CLI | LoRA + QLoRA)
→ Fine-tune LLMs with LoRA and QLoRA→ Use WebUI and CLI for fine-tuning→ Configure essential parameters for fine-tuning
LLM Fine-Tuning Crash Course: Finetune model on PDFs, Instruction FT, Preference Training (DPO/RLHF)
→ Fine-tune LLMs on custom datasets→ Adapt LLMs to specific domains→ Improve instruction-following capabilities
DeepCamp AI