Tutorial Helper

• Llama 2 - Build Your Own Text Generation API with Llama 2 - on RunPod, Step-by-Step

• YouTube Tutorial: https://youtu.be/Ftb4vbGUr7U

• Create a RunPod account: https://runpod.io/

• Postman config: llama2-serverless-api.postman_collection.json

• Llama GPTQ Model

  • TheBloke/Llama-2-13B-chat-GPTQ

  • https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ 

• Pre-built docker image:

  • generativelabs/exllama-runpod-serverless:1.0.0

  • ​https://hub.docker.com/r/generativelabs/exllama-runpod-serverless

• If you want to create your own Docker image:

  • git clone https://github.com/generativelabs/exllama-runpod-serverless.git​​

  • sudo DOCKER_BUILDKIT=1 docker build .

  • docker images (get the IMAGEID for your the image)

  • docker tag IMAGEID your-account/your-image-name:1.0.0

  • docker push your-account/your-image-name:1.0.0

• Did this tutorial save you time? Make a contribution

​

Tutorial Helper

• Building a Text Generation API with Open Source LLMs: Easy Step-by-Step Guide

• YouTube Tutorial: https://youtu.be/kKkWuxaXfqM

• Create a RunPod account: https://runpod.io/

• Postman config: exllama-serverless-api.postman_collection.json

• Pick out your GPTQ LLM

  • Video uses: ​TheBloke/airoboros-7B-gpt4-1.4-GPTQ

  • You can use any GPTQ Llama model.

  • See this Hugging Face link for other GPTQ llama models you can use

• Pre-built docker image:

  • generativelabs/exllama-runpod-serverless:1.0.0

  • ​https://hub.docker.com/r/generativelabs/exllama-runpod-serverless

• If you want to create your own Docker image:

  • git clone https://github.com/generativelabs/exllama-runpod-serverless.git​​

  • sudo DOCKER_BUILDKIT=1 docker build .

  • docker images (get the IMAGEID for your the image)

  • docker tag IMAGEID your-account/your-image-name:1.0.0

  • docker push your-account/your-image-name:1.0.0

• Did this tutorial save you time? Make a contribution

​

Tutorial Helper

• RunPod Stable Diffusion, Serverless Complete Tutorial

• YouTube Tutorial: https://youtu.be/ojwEOdj7iUI 

• Create a RunPod account: https://runpod.io/

• ​git clone https://github.com/generativelabs/worker-a1111.git

• Postman config: postman-config-runpod-serverless.json 

• Read my "Lessons Learned - RunPod Serverless" Blog Post

• Trouble Shooting

  • On Mac, if you run into "gcc"missing error, add: --platform linux/amd64 to docker build command ​

• Did this tutorial save you time? Make a contribution

​

Tutorial Helper

• Setting Up a Stable Diffusion API with Control Net using RunPod Serverless

• YouTube Tutorial: https://youtu.be/gv6F9Vnd6io

• Create a RunPod account: https://runpod.io/​

• Postman config: A1111 ControlNet with RunPod Serverless.json

• Base 64 encoder: https://www.base64-image.de/

• If you want to create your own Docker image:

  • ​​git clone https://github.com/generativelabs/serverless-pod-a1111.git

  • sudo DOCKER_BUILDKIT=1 docker build .

  • docker images (get the IMAGEID for your the image)

  • docker tag IMAGEID your-account/your-image-name:1.0.0

  • docker push your-account/your-image-name:1.0.0

• ControlNet API documentation:  https://github.com/Mikubill/sd-webui-controlnet/wiki/API#web-api

• Did this tutorial save you time? Make a contribution

​

Tutorial Helper​

• Using OpenPose and ControlNet with Stable Diffusion on RunPod

• YouTube Tutorial: https://youtu.be/n0mJRoMf5H4

• Create a RunPod account: https://runpod.io/

• Extension install from URL: https://github.com/fkunn1326/openpose-editor

• Read my "Using OpenPose with ControlNet" Blog Post

• ​Did this tutorial save you time? Make a contribution

​

​