Model Hyperparameters
temperature represents the sampling temperature. Higher values (such as 0.8) will make the output more random, while lower values (such as 0.2) will make the output more deterministic.
top_p represents the probability threshold for nucleus sampling, used to control the diversity of text generated by the model. The higher the value, the greater the diversity of the generated text.
In thinking mode, the mimo-v2.5-pro, mimo-v2.5, mimo-v2-pro and mimo-v2-omni models do not support customizing the temperature and top_p parameters. Even if these parameters are passed in, the actual effective values will be forcibly set by the model to its recommended default values of 1.0 and 0.95.
The default values and parameter ranges of temperature and top_p for different models are as follows:
| Model Name | temperature | top_p |
|---|---|---|
mimo-v2.5-promimo-v2-pro |
|
|
mimo-v2.5mimo-v2-omni |
|
|
mimo-v2.5-ttsmimo-v2.5-tts-voicedesignmimo-v2.5-tts-voiceclonemimo-v2-tts |
|
|
mimo-v2-flash |
|
|
We recommend that you set parameter values according to task type, and you can refer to the following recommended values.
The recommended values for the mimo-v2-flash model are as follows:
| Task Type | temperature | top_p |
|---|---|---|
| Vibe Coding | 0.3 | 0.95 |
| Function Call | 0.3 | 0.95 |
| General Conversation | 0.8 | 0.95 |
| Creative Writing | 0.8 | 0.95 |
| WebDev | 0.8 | 0.95 |
| Mathematical Reasoning | 1 | 0.95 |
The recommended values for the temperature and top_p parameters of the mimo-v2.5-pro, mimo-v2.5, mimo-v2-pro, and mimo-v2-omni models for the above tasks are 1.0 and 0.95, respectively.