You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The current explainer for parameters settings are not clear enough according to user feedback:
We need to guide user's how to set it effectively (directly in app, not just through docs).
Success Criteria
Explainers should be short, precise, straight to the point
Setting parameters explainer
Inference Parameters
Parameter
Description
Temperature
Influences the randomness of the model's output. A higher value leads to more random and diverse responses, while a lower value produces more predictable outputs.
Top P
Set probability threshold for more relevant outputs. A lower value (e.g., 0.9) may be more suitable for focused, task-oriented applications, while a higher value (e.g., 0.95 or 0.97) may be better for more open-ended, creative tasks.
Stream
Enables real-time data processing, which is useful for applications needing immediate responses, like live interactions. It accelerates predictions by processing data as it becomes available.
Max Tokens
Sets the upper limit on the number of tokens the model can generate in a single output. A higher limit benefits detailed and complex responses, while a lower limit helps maintain conciseness.
Stop Sequences
Defines specific tokens or phrases that signal the model to stop producing further output, allowing you to control the length and coherence of the output.
Frequency Penalty
Modifies the likelihood of the model repeating the same words or phrases within a single output. Increasing it can help avoid repetition, which is useful for scenarios where you want more varied language, like creative writing or content generation.
Presence Penalty
Reduces the likelihood of repeating tokens, promoting novelty in the output. Use a higher value for tasks requiring diverse ideas.
Model Parameters
Parameter
Description
Prompt Template
A predefined text or framework that guides the AI model's response generation. It includes placeholders or instructions for the model to fill in or expand upon.
Engine Parameters
Parameter
Description
Context Length
Sets the maximum input the model can use to generate a response, it varies with the model used. Higher length is better for tasks needing extensive context, like summarizing long documents. Lower length can improve response time and reduce computing needs for simple queries.
The text was updated successfully, but these errors were encountered:
Problem
The current explainer for parameters settings are not clear enough according to user feedback:
We need to guide user's how to set it effectively (directly in app, not just through docs).
Success Criteria
Explainers should be short, precise, straight to the point
Setting parameters explainer
Inference Parameters
Model Parameters
Engine Parameters
The text was updated successfully, but these errors were encountered: