Files
zeekay 99f352f413 🎮 Add local training demos and GSPO implementation test
- Create demo_training.py for full training workflow
- Add simple_demo.py showing GSPO algorithm concepts
- Demonstrate group normalization and sequence-level optimization
- Show memory savings (40-60% vs PPO)
- Ready for local training with Qwen3 models

Run locally with:
$ python simple_demo.py
$ gym-cli train --stage gspo --config configs/gspo_qwen3_4b_nano.yaml
2025-09-25 01:20:48 -05:00

27 lines
1.2 KiB
JSON

[
{
"instruction": "What is machine learning?",
"input": "",
"output": "Machine learning is a branch of artificial intelligence that enables systems to learn and improve from experience without being explicitly programmed."
},
{
"instruction": "Explain neural networks",
"input": "",
"output": "Neural networks are computing systems inspired by biological neural networks that constitute animal brains. They consist of interconnected nodes that process information."
},
{
"instruction": "What is GSPO?",
"input": "",
"output": "GSPO (Group Sequence Policy Optimization) is a reinforcement learning algorithm that performs sequence-level optimization, providing superior training stability for large language models."
},
{
"instruction": "Write a Python hello world program",
"input": "",
"output": "Here's a simple Python hello world program:\n\n```python\nprint('Hello, World!')\n```"
},
{
"instruction": "What are the benefits of exercise?",
"input": "",
"output": "Exercise provides numerous benefits including improved cardiovascular health, stronger muscles and bones, better mental health, weight management, and increased energy levels."
}
]