...
- defines, if the default system-message of a training (the topmost message in the training-window) is used when pretranslating with the model. Until this system-message will be editable, the following will be used:
"You are a machine translation engine and translate single texts or multiple segments {fullFromTo}" - when this is de-selected, only the following system-message will be used when pretranslation with the model:
"Translate the following segments encapsulated in JSON Objects with the index and the segment as properties {fullFromTo} using all segments as context for each other"
Use user defined system-messages when translating:
...
- Temperature is a parameter that governs the randomness and thus the creativity of the responses. It is always a number between 0 and 1. A temperature of 0 means the responses will be very straightforward, almost deterministic (meaning you almost always get the same response to a given prompt) A temperature of 1 means the responses can vary wildly. It’s advisable to adjust either the temperature or top_p, but not both. Further information: https://medium.com/@1511425435311/understanding-openais-temperature-and-top-p-parameters-in-language-models-d2066504684f
Probability Threshold / Top P:
The "top P"parameter, also known as nucleus sampling, is a nuanced alternative to temperature-based sampling. It is a "spotlight" that shines on the most probable words. At a default value of 1.0, the model considers all words. This parameter can help control the distribution of word choices, keeping the generated content relevant and coherent.It’s advisable to adjust either the temperature or top_p, but not both. Further information: https://medium.com/@1511425435311/understanding-openais-temperature-and-top-p-parameters-in-language-models-d2066504684f
Presence Penalty:
- This parameter is used to encourage the model to include a diverse range of tokens in the generated text. It is a value that is subtracted from the log-probability of a token each time it is generated. A higher presence_penalty value will result in the model being more likely to generate tokens that have not yet been included in the generated text. Further information: https://medium.com/@KTAsim/frequency-vs-presence-penalty-whats-the-difference-openai-api-51b0c4a7229e
Frequency Penalty:
- This parameter is used to discourage the model from repeating the same words or phrases too frequently within the generated text. It is a value that is added to the log-probability of a token each time it occurs in the generated text. A higher frequency_penalty value will result in the model being more conservative in its use of repeated tokens. Further information: https://medium.com/@KTAsim/frequency-vs-presence-penalty-whats-the-difference-openai-api-51b0c4a7229e
Max. target tokens (% of source tokens):
...