Chat Test

Load or connect a trained model and check the fine-tuning results by chatting with it directly.

Loading a Model into the Inference Server

Load a trained model directly to test it.

• Model path: Enter the path of the model to test (e.g., /@team/.AppData/fine_tuning/runs/model)
• Adapter path (optional): If you're using only the adapter weights trained separately, such as via LoRA, specify the path here
• Template: Automatically detected by default

After entering the path, click the Start button to launch the inference server.

Connecting to an Ollama Server

You can also test directly with a model already registered in Ollama. In the Connect area, enter the server (Ollama) and model name (e.g., gemma4:12b), then check the connection status with the refresh button. Click the Reset button to start the setup over.

Checking Results Through Conversation

Enter a message in the input box at the bottom and send it with Ctrl+Enter (or the send button); the user message and the AI's response are displayed as a chat. Ask questions relevant to your training goal to check the quality and format of the responses.

Good to Know

• A model that has only completed PT (pre-training) may produce continuation-style responses rather than instruction-following conversation. To check instruction-following quality, test with a model that has also completed SFT.
• If you specify only the adapter path and leave the model path blank, it may not load correctly.

Related Documents

• Evaluation
• Export