# Using StarCoder + Tech Assistant prompt to help write code

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-starcoder-tech-assistant-prompt-to-help-write-code%2F49728%3E%5C
**Category:** Beginners\
**Created:** [August 6, 2023, 11:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-starcoder-tech-assistant-prompt-to-help-write-code%2F49728 "2023-08-06T23:18:25Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![pvelosipednikov](https://avatars.discourse-cdn.com/v4/letter/p/90db22/32.png) [@pvelosipednikov](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fpvelosipednikov)%5C
**Post date:** [August 6, 2023, 11:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fusing-starcoder-tech-assistant-prompt-to-help-write-code%2F49728%2F1 "2023-08-06T23:18:25Z")

</div>

Hello. I’m starting out in my HuggingFace journey with the intent of using an LLM to expedite feature development in a codebase.

I understand that StarCoder seems to be the way to go and my idea is to fine-tune it on my code. But the [page](https://huggingface.co/bigcode/starcoder) explicitly states the following:

> As such it is not an instruction model and commands like “Write a function that computes the square root.” do not work well. However, by using the Tech Assistant prompt you can turn it into a capable technical assistant.

The Tech Assistant prompt appears to be a training set of 650 records. This seems way too small to be sufficiently versatile. Is this the recommended combination of tools for my purpose (to build an LLM which I can ask to generate new code) or are there other approaches in the HuggingFace ecosystem?

Thanks