get_model_recommendations
Calculate adaptive sampling parameters (min_p, temperature, top_p, num_ctx, repeat_penalty) from model parameter size and query complexity to optimize LLM generation.
Instructions
Calculates adaptive sampling parameters (min_p, temperature, top_p, num_ctx, repeat_penalty) based on LLM parameter size and query complexity.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model_name": "<model_name>"
},
"name": "get_model_recommendations"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| warmth | No | Pastoral sensitivity (0 to 100) | |
| model_name | Yes | Name of the target LLM | |
| user_message | No | User's prompt message | |
| parameter_size_b | No | Parameter count in Billions |