Response cutoff

Beginners
1

I am trying to use a model for text generation with the inference endpoint with Javascript but currently my responses are just being cut off

const text = ' """<｜fim▁begin｜> def fibonnaci(): <｜fim▁hole｜> <｜fim▁end｜> """'
const { generated_text } = await gpt2.textGeneration({ inputs: `${text}`, max_new_tokens: 500})
console.log(generated_text)

Below is the output I get, how do I increase the size returned I assumed it was to increase max_new_tokens. Any help appreciated


    fibonnaci = [0, 1]
    while len(fib```
2 
const text = ' """<｜fim▁begin｜> def fibonnaci(): <｜fim▁hole｜> <｜fim▁end｜> """'
const { generated_text } = await gpt2.textGeneration({ inputs: `${text}`, parameters: {max_new_tokens: 500} })
console.log(generated_text)