Skip to content

armgit / Soup

Public Imported from GitHub
0

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

3.7 KB
Raw Blame
{"prompt": "What is machine learning?", "chosen": [{"role": "user", "content": "What is machine learning?"}, {"role": "assistant", "content": "Machine learning is a field of artificial intelligence where systems learn from data automatically. It uses algorithms to identify patterns and improve performance through experience, without being explicitly programmed for every task."}], "rejected": [{"role": "user", "content": "What is machine learning?"}, {"role": "assistant", "content": "Machine learning replaces data with rules written by programmers. The computer follows them exactly and gives the same answer every time, so training examples or feedback are unnecessary after compilation for deployment."}]}
{"prompt": "How do I learn Python?", "chosen": [{"role": "user", "content": "How do I learn Python?"}, {"role": "assistant", "content": "Here are effective ways to learn Python:\n1. Start with fundamentals: variables, loops, functions\n2. Practice with small projects\n3. Use resources like Python.org docs and tutorials\n4. Build projects to apply what you learn\n5. Join communities for support"}], "rejected": [{"role": "user", "content": "How do I learn Python?"}, {"role": "assistant", "content": "Learn every built-in function and the standard library before writing a program. Avoid small projects because mistakes reinforce bad habits. Copy solutions until the syntax feels familiar, and postpone reading errors or asking for feedback until you can code alone."}]}
{"prompt": "What's the difference between AI and ML?", "chosen": [{"role": "user", "content": "What's the difference between AI and ML?"}, {"role": "assistant", "content": "AI (Artificial Intelligence) is the broader field of creating intelligent systems. ML (Machine Learning) is a subset of AI focused on learning from data. All machine learning is AI, but not all AI uses machine learning."}], "rejected": [{"role": "user", "content": "What's the difference between AI and ML?"}, {"role": "assistant", "content": "AI and machine learning are interchangeable names for programs that make decisions. Both always learn from examples, so rule-based expert systems are machine-learning models. Researchers usually say AI, while software companies prefer the newer ML label."}]}
{"prompt": "Explain neural networks simply.", "chosen": [{"role": "user", "content": "Explain neural networks simply."}, {"role": "assistant", "content": "Neural networks are inspired by the human brain. They consist of layers of connected nodes (neurons) that process information. Each connection has a weight that adjusts during training. This allows the network to learn complex patterns in data."}], "rejected": [{"role": "user", "content": "Explain neural networks simply."}, {"role": "assistant", "content": "A neural network stores training examples in a chain of neurons. For input, it searches those examples and copies the closest answer. Training only adds more neurons without changing connections, so a larger dataset makes the model larger."}]}
{"prompt": "How should I structure a machine learning project?", "chosen": [{"role": "user", "content": "How should I structure a machine learning project?"}, {"role": "assistant", "content": "Follow this structure:\n1. Define the problem and gather data\n2. Explore and clean the data\n3. Choose and train a model\n4. Evaluate performance\n5. Iterate and improve\n6. Deploy to production\n7. Monitor and maintain"}], "rejected": [{"role": "user", "content": "How should I structure a machine learning project?"}, {"role": "assistant", "content": "Keep experiments, training, evaluation, and deployment in one script. Tune on the test set until the score is high, save the best weights, and skip versioning data or configuration because the source file records it."}]}