1.3 - LLM difference

You can easily download and run the workflow directly in your KNIME installation. We recommend that you use the latest version of the KNIME Analytics Platform for optimal performance.

This workflow compares the outputs generated by OpenAI's gpt-3.5-turbo-instruct (costs $0.0017 / 1K tokens) and the Hugging Face Hub text generation model zephyr-7b-alpha (free to use).

The workflow requires both an OpenAI API key and a Hugging Face Hub access token.

Instructions:

1. If you don't have one yet, register with OpenAI and create a new API key under https://platform.openai.com/account/api-keys.

2. If you don't already have one, create an account on https://huggingface.co/, go to https://huggingface.co/settings/tokens and create a new token.

2. This workflow uses "HuggingFaceH4/zephyr-7b-alpha" model. Text generating models can be found at Hugging Face Hub (see external resources).

External resources

• OpenAI API Keys
• Hugging Face Hub Access Tokens
• Hugging Face Hub