async generator and token stream

[TareHimself]

Describe your changes

Added streaming and Async generator and also correct token count for response tokens

Issue ticket number and link

Checklist before requesting a review

• I have performed a self-review of my code.
• If it is a core feature, I have added thorough tests.
• I have added thorough documentation for my code.
• I have tagged PR with relevant project labels. I acknowledge that a PR without labels may be dismissed.
• If this PR addresses a bug, I have provided both a screenshot/video of the original bug and the working solution.

Demo

The following was streamed token by token

Response:  I'm doing well, thank you for asking! How can I help you today?

Steps to Reproduce

import gpt from '../src/gpt4all.js'

const model = await gpt.loadModel("mistral-7b-openorca.Q4_0.gguf")  

process.stdout.write('Response: ')

for await (const token of gpt.generateTokens(model,[{
    role: 'user',
    content: "How are you ?"
  }],{nPredict: 2048 })){
    process.stdout.write(token);
  }

model.dispose();

Notes