Choices

You can specify a list of preferred words (choices) in the script metadata. It will increase the probability of the model generating the specified words.

• Each word should match a single token for the desired model!
• For some models, GenAIScript does not have a token encoder so it won’t be able to compute the logit bias for the choices

script({
    choices: ["OK", "ERR"],
})
...

ERR

Custom weights

You can tune the probability of each choice by providing a weight for each choice. The default weight is 5.

script({
    choices: ["OK", { token: "ERR", weight: 10 }],
})

Pre-encoded tokens

For models where GenAIScript does not have a token encoder, you can provide the pre-encoded tokens.

script({
    choices: [{ token: 12345, weight: 10 }],
})

Logit Bias

Internally, GenAIScript tokenizes the word and build the logit_bias for each token.

• choices: OK, ERR
• logit bias: {"5175":5,"5392":5}

Logprobs

You can enable logprobs to visualize the confidence of the tokens generated by the model.

---

ERR .

---