Note: These settings will be used as defaults for all requests to this Ollama instance. They can be overridden on a per-request basis.

• Context Length: Longer context allows the model to consider more previous text but uses more memory.
• Temperature: Higher values (>1.0) make output more random, lower values make it more focused and deterministic.
• Top P: Controls diversity via nucleus sampling. Lower values (0.1) are more focused, higher values (0.9) more diverse.
• Top K: Limits the cumulative probability of tokens to sample from. Lower values are more focused.
• Repeat Penalty: Higher values (>1.0) make the model less likely to repeat itself.