# Prediction on Causal Language models

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fprediction-on-causal-language-models%2F132573%3E%5C
**Category:** Beginners\
**Created:** [December 22, 2024, 1:47am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fprediction-on-causal-language-models%2F132573 "2024-12-22T01:47:17Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![mattsauer](https://avatars.discourse-cdn.com/v4/letter/m/8491ac/32.png) [@mattsauer](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmattsauer)%5C
**Post date:** [December 22, 2024, 1:47am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fprediction-on-causal-language-models%2F132573%2F1 "2024-12-22T01:47:17Z")

</div>

Hello, I am trying to make a causal language model in tensorflow. Labels are shifted internally in the model. I need a bit more control over the labels then that. How can I store them somewhere?