How to Get your LLMs to OBEY | Easiest Fine-tuning Interface for Total Control over your LLMs

In this video, we will explore how to easily fine-tune LLaMA-3.2-1B-Instruct using a simple dataset to make it respond according to our preferences. We will utilize LLaMA Factory, which simplifies the fine-tuning process, all within a Gradio GUI Interface—it's truly amazing!

Compared to ChatGLM's P-Tuning, LLaMA Factory's LoRA tuning offers up to 3.7 times faster training speeds with improved Rouge scores in advertising text generation tasks. By utilizing 4-bit quantization, QLoRA further enhances efficiency in terms of GPU memory usage.

Learn More:
Github: github.com/hiyouga/LLaMA-Factory
Colabs: colab.research.google.com/drive/1eRTPn37ltBbYsISy9…
Paper: arxiv.org/abs/2403.13372

#LLaMAFactory #LoRATuning #FineTuning #AITraining #MachineLearning #GradioGUI #QLoRA #AIEfficiency #GPTuning #4bitQuantization #AIFineTuning

Features
• Various models: LLaMA, LLaVA, Mistral, Mixtral-MoE, Qwen, Qwen2-VL, Yi, Gemma, Baichuan, ChatGLM, Phi, etc.
• Integrated methods: (Continuous) pre-training, (multimodal) supervised fine-tuning, reward modeling, PPO, DPO, KTO, ORPO, etc.
• Scalable resources: 16-bit full-tuning, freeze-tuning, LoRA and 2/3/4/5/6/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8/HQQ/EETQ.
• Advanced algorithms: GaLore, BAdam, Adam-mini, DoRA, LongLoRA, LLaMA Pro, Mixture-of-Depths, LoRA+, LoftQ, PiSSA and Agent tuning.
• Practical tricks: FlashAttention-2, Unsloth, Liger Kernel, RoPE scaling, NEFTune and rsLoRA.
• Experiment monitors: LlamaBoard, TensorBoard, Wandb, MLflow, etc.
• Faster inference: OpenAI-style API, Gradio UI and CLI with vLLM worker.

CHANNEL LINKS:
🕵️‍♀️ Join my Patreon for keeping up with the updates: www.patreon.com/PromptEngineer975
☕ Buy me a coffee: ko-fi.com/promptengineer
📞 Get on a Call with me at $125 Calendly: calendly.com/prompt-engineer48/call
💀 GitHub Profile: github.com/PromptEngineer48
🔖 Twitter Profile: twitter.com/prompt48

Other videos that you would love:

   • OpenAI's SWARM is the Ultimate Multi-...  
   • Smart AI Flight Recommendation System...  
   • The AI Framework That Thinks and Acts...  
   • Palmyra Tool Calling Ability EXPOSED!...  
   • Private Chat with your Documents with...  
   • Unlock Ollama's Modelfile | How to Up...  
   • DEVIKA | Getting Started [A-Z] Instal...  
   • CrewAI is Better than AutoGEN ?? Use ...  

0:00 Intro
0:44 Llama Factory Intro
2:16 Colab Notebook
3:30 Starting the Training
4:00 Choosing the Dataset
4:58 Comparison of Chats
5:53 Finetuning Works
6:38 Conclu