Hi, I am fine-tuning LLAMA on a multiple-choice question-answering (MCQA) dataset. During the training phase, would it be a good approach to trim the model’s output head to just four tokens corresponding to the answer options, so that during the generation phase, the model is constrained to generate only the labels? Are there any alternative strategies I could consider for achieving this?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Finetuning llama for classification | 2 | 1100 | January 21, 2025 | |
| A fine tuned Llama2-chat model can't answer questions from the dataset | 0 | 310 | December 20, 2023 | |
| Fine-tune model with CoT | 1 | 464 | January 27, 2025 | |
| A fine tuned Llama2-chat model can’t answer questions from the dataset | 0 | 247 | December 23, 2023 | |
| Training loss is zero from the first step and model generation is empty after training? | 0 | 369 | February 8, 2024 |