​

Having Conversations

​

Sending Messages

1. Type your message in the input box
2. Press Enter or click Send
3. Wait for the model to respond
4. Continue the conversation

​

Conversation Context

• Each message you send includes previous context
• The model “remembers” what you’ve discussed
• Longer conversations use more memory

​

Context Window

​

Conversation Tips

​

For Testing Fine-tuned Models

Training data: Customer support conversations
Test prompt: "I can't log into my account"

Training data: Code generation
Test prompt: "Write a Python function to sort a list"

​

For Evaluating Quality

• Factual: “What is the capital of France?”
• Reasoning: “If A > B and B > C, is A > C?”
• Creative: “Write a haiku about programming”
• Domain-specific: Questions from your fine-tuning domain

​

For Finding Issues

• Very short inputs (“Hi”)
• Very long inputs
• Unusual characters or formatting
• Questions outside training domain
• Attempts to confuse the model

​

Clearing History

• Look for “Clear” or “New Chat” button
• Or reload the page

• Testing different scenarios
• Context gets too long
• Starting a new demo

​

Multi-turn Conversations

User: What's 2 + 2?
Assistant: 4

User: And if we add 3 more?
Assistant: That would be 7 (4 + 3 = 7)

​

Common Patterns

​

Question-Answer Testing

User: [Question]
Assistant: [Answer]
User: Can you explain that differently?
Assistant: [Reformulated answer]

​

Instruction Following

User: Write a poem about cats. Make it exactly 4 lines.
Assistant: [Poem]
User: Now make it about dogs instead
Assistant: [Modified poem]

​

Role-Playing

User: You are a helpful customer service agent. A customer says: "My order is late"
Assistant: [Response in character]

​

Next Steps