# LLAMA for MCQA dataset

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama-for-mcqa-dataset%2F136728%3E%5C
**Category:** Beginners\
**Created:** [January 21, 2025, 6:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama-for-mcqa-dataset%2F136728 "2025-01-21T18:07:19Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ayushp12](https://avatars.discourse-cdn.com/v4/letter/a/e99b99/32.png) [@ayushp12](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fayushp12)%5C
**Post date:** [January 21, 2025, 6:07pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fllama-for-mcqa-dataset%2F136728%2F1 "2025-01-21T18:07:19Z")

</div>

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?