# Custom NER with ~54 entities

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcustom-ner-with-54-entities%2F40896%3E%5C
**Category:** Community Calls\
**Created:** [May 25, 2023, 1:30am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcustom-ner-with-54-entities%2F40896 "2023-05-25T01:30:32Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![M3Z47](https://avatars.discourse-cdn.com/v4/letter/m/6f9a4e/32.png) [@M3Z47](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FM3Z47)%5C
**Post date:** [May 25, 2023, 1:30am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fcustom-ner-with-54-entities%2F40896%2F1 "2023-05-25T01:30:32Z")

</div>

Hello,

I want to fine tune a LLM for my 54 entities. Could anyone guide how to pass these entities with their keywords and synonyms to a llm and fine tune it with training data? I can generate training queries for these entities but I can’t get around how to map word by word tokens with their embeddings and fine tune it.  
Please help. Thanks