npm i -g @cli-me/cli

Workflow Detail

AI Inference

Authenticate model providers and execute inference runs.

Overview
3 steps~25 minaimlinference

Required env vars: HF_TOKEN, REPLICATE_API_TOKEN

Auth needed for: Hugging Face CLI, Replicate CLI

Step By Step
Step 1Ollama CLI

Execute Ollama CLI stage in ai inference workflow.

ollama serve

Start ollama

ollama create

Create a model

Step 2Hugging Face CLIAuth required

Execute Hugging Face CLI stage in ai inference workflow.

Authentication

  • Step 1 Export required environment variables: HF_TOKEN

huggingface-cli download

Download files from the Hub

huggingface-cli upload

Upload a file or a folder to a repo on the Hub

Step 3Replicate CLIAuth required

Execute Replicate CLI stage in ai inference workflow.

Authentication

  • Step 1 Export required environment variables: REPLICATE_API_TOKEN

replicate login

Authenticate model provider account

replicate models

List available models