Name		Name	Last commit message	Last commit date
parent directory ..
Llama2.aifile		Llama2.aifile
Llama2_with_knowledge.aifile		Llama2_with_knowledge.aifile
OpenAssistant_Falcon_7B.aifile		OpenAssistant_Falcon_7B.aifile
OpenAssistant_Falcon_7B_with_knowledge.aifile		OpenAssistant_Falcon_7B_with_knowledge.aifile
README.md		README.md
example_german_speaking_assistant.aifile		example_german_speaking_assistant.aifile
example_ollie_the_dog.aifile		example_ollie_the_dog.aifile
example_personal_assistant_to_bob.aifile		example_personal_assistant_to_bob.aifile
example_python_coding_assistant.aifile		example_python_coding_assistant.aifile
huggingface_textgen_inference.aifile		huggingface_textgen_inference.aifile

README.md

Hugging Face TextGen Inference

Text Generation Inference is a Rust, Python and gRPC server for text generation inference.

This allows you to run Hugging Face Hub models and other LLMs on your own infrastructure.

Set up the Text Generation Inference server.
Download the aifile and load it with ownAI (in ownAI, click on the logo in the upper left corner to open the menu, then select "AI Workshop", then "New AI" and "Load Aifile").
Set the inference_server_url setting in the aifile to the URL of your server.

These AIs are running on your own machine or on a server where you install the inference server.