Launching the Chat Interface

The Chat interface lets you interact with your trained models in a browser.

Quick Start

aitraining chat

The browser will open automatically to http://localhost:7860/inference.

Command Options

aitraining chat [OPTIONS]

Options:
  --port PORT    Port to run on (default: 7860)
  --host HOST    Host to bind to (default: 127.0.0.1)

Examples

# Default (localhost:7860)
aitraining chat

# Custom port
aitraining chat --port 3000

# Accessible from other machines
aitraining chat --host 0.0.0.0 --port 7860

Requirements

Before launching, you need:

A trained model (local path or Hugging Face model ID)
Sufficient memory to load the model

Typical Workflow

Train a model:

aitraining llm --train \
  --model meta-llama/Llama-3.2-1B \
  --data-path ./my-data \
  --project-name my-model

Launch chat:
aitraining chat
Browser opens automatically to localhost:7860/inference
Load your trained model from ./my-model
Start chatting

Stopping the Server

Press Ctrl+C in the terminal to stop the chat server.

Troubleshooting

Port already in use

Another process is using port 7860. Either:

Stop the other process
Use a different port: aitraining chat --port 3000

Model won't load

Check:

Model path is correct
Sufficient GPU/RAM memory
Model format is compatible (Hugging Face format)

Can't access from other machines

Use --host 0.0.0.0 to bind to all interfaces:

aitraining chat --host 0.0.0.0

Next Steps

Interface Overview

Learn the chat interface

Loading Models

Load and switch models

Interface Overview

​Launching the Chat Interface

​Quick Start

​Command Options

​Examples

​Requirements

​Typical Workflow

​Stopping the Server

​Troubleshooting

​Next Steps

Interface Overview

Loading Models

Launching the Chat Interface

Quick Start

Command Options

Examples

Requirements

Typical Workflow

Stopping the Server

Troubleshooting

Next Steps