Deploying a Model on Runpod using Hugging Face

My Endpoints

  1. 1. Serverless page

    Serverless page

  2. 2. Click on Start vLLM

    Click on Start vLLM

  3. 3. Click on organization/model-name

    Click on organization/model-name

My Endpoints

  1. 4. Paste "https://huggingface.co/mychen76/huggin_face_model" into input

    Paste "https://huggingface.co/mychen76/huggin_face_model" into input

  2. 5. Click on Next

    Click on Next

  3. 6. Choose GPU of choice

    Choose GPU of choice

  4. 7. Click on Deploy

    Click on Deploy