Petr Royce PRO
0xroyce
AI & ML interests
Multimodal Models, Synthetic Data Generation, Model Fine-Tuning (LoRA, QLoRA, Unsloth), Agentic Systems, Reinforcement Learning, Efficient Training, Training Frameworks, Edge Deployment of LLMs
Recent Activity
updated a dataset about 21 hours ago
EloPhanto/dataset new activity 1 day ago
0xroyce/Plutus-3B:Fine-tuning Llama 3.2 for stock market and trading analysis updated a dataset 3 days ago
EloPhanto/dataset