Manage inference configuration settings for text generation. This command allows you to view, modify, and reset generation parameters like temperature, top-p, and max tokens.
python -m wisent inference-config [show|set|reset] [OPTIONS]
python -m wisent inference-config show
python -m wisent inference-config set --temperature 0.7
python -m wisent inference-config set \ --temperature 0.8 \ --top-p 0.95 \ --max-new-tokens 256 \ --do-sample true
python -m wisent inference-config set --enable-thinking true
python -m wisent inference-config reset
| Subcommand | Description |
|---|---|
| show | Display current inference configuration |
| set | Update inference configuration values |
| reset | Reset configuration to default values |
| Argument | Type | Description |
|---|---|---|
| --do-sample | bool | Enable sampling (true/false) |
| --temperature | float | Sampling temperature (e.g., 0.7) |
| --top-p | float | Top-p (nucleus) sampling (e.g., 0.9) |
| --top-k | int | Top-k sampling (e.g., 50) |
| --max-new-tokens | int | Max new tokens to generate |
| --repetition-penalty | float | Repetition penalty (e.g., 1.0) |
| --no-repeat-ngram-size | int | No repeat n-gram size |
| --enable-thinking | bool | Enable thinking mode for Qwen3 models |
Stay in the loop. Never miss out.
Subscribe to our newsletter and unlock Wisent insights.