Icon

1.2 - HuggingFace Hub

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.

Hugging Face is a platform that helps developers and researchers work with language-related tasks, like understanding and generating text.
It provides tools and libraries that make it easier to build and use models for tasks like classifying text, understanding sentiment, and translating languages.

Instructions:

1. In order to run this workflow you need an access token for Hugging Face Hub.
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 "HuggingFace/zephyr-7b-alpha" model. Text generating models can be found at Hugging Face Hub (see external resources).
Models must be able to use the Inference API.

URL: Hugging Face Hub https://huggingface.co/
URL: Hugging Face Hub Access Tokens https://huggingface.co/settings/tokens
URL: Hugging Face Hub Models https://huggingface.co/models?pipeline_tag=text-generation&sort=trending

Prompt Hugging Face Hub LLMs

  • This workflow shows how to connect to an LLM on Hugging Face Hub and send prompts to it.

  • In order to run this workflow you need an access token for Hugging Face Hub.
    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.

  • To learn more about the workflow, click the left bar and check the description section.


Completions

A Large Language Model is used for completions, which means it can generate human-like text based on a given input. It is used for a wide range of natural language understanding and generation tasks, such as content generation, text summarization, translation, classification and question answering. It is not indented for chatting.

Hugging Face Models

Note that the free Hugging Face hosted models may not be on par with the ones from OpenAI. You may be able to receive better results by altering the prompts given to the models.

Enter theHugging Face Hubaccess token
Credentials Configuration
LLM Prompter
Authenticate withHugging Face API Key
HF Hub Authenticator
Get a text generatingmodel from the hub
HF Hub LLM Connector
Completion prompts
Table Creator

Nodes

Extensions

Links