replicate/flan-t5-xl

A language model by Google for tasks like classification, summarization, and more

Input
Configure the inputs for the AI model.

provide debugging output in logs

0.01
1

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Prompt to send to FLAN-T5.

1
100

Maximum number of tokens to generate. A word is generally 2-3 tokens

0.01
5

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

0.01
5

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.

flan-t5-xl - ikalos.ai