1Cademy - Inference Process with a Fine-Tuned Model

Learn Before

Fine-Tuning Pre-trained Models for Downstream Tasks
Tokenization
Maximum Probability Decision Rule
Probability Computation with Pre-trained Language Models

Activity (Process)

Inference Process with a Fine-Tuned Model

Once a model's parameters have been optimized through fine-tuning, the resulting model, denoted as $F_{\tilde{\omega},\tilde{\theta}}(\cdot)$ , can be used for inference on new, unseen data. For instance, in a text classification task, the new text is first tokenized into a sequence of tokens, represented as $\mathbf{x}_{\mathrm{new}}$ . This token sequence is then fed into the fine-tuned model, which processes it to generate a probability distribution over the possible classes.