# Advice on LLMs that can be used directly in Python

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fadvice-on-llms-that-can-be-used-directly-in-python%2F121730%3E%5C
**Category:** Beginners\
**Created:** [November 15, 2024, 4:17am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fadvice-on-llms-that-can-be-used-directly-in-python%2F121730 "2024-11-15T04:17:26Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![l-elborough](https://avatars.discourse-cdn.com/v4/letter/l/a88e4f/32.png) [@l-elborough](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fl-elborough)%5C
**Post date:** [November 15, 2024, 4:17am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fadvice-on-llms-that-can-be-used-directly-in-python%2F121730%2F1 "2024-11-15T04:17:26Z")

</div>

Hi, I am hoping for some advice for a project that I am working on.  
My problem is classifying company names into industry groups, and I’m looking for a small LLM to do so, that I can read directly into Python and use from there. Unfortunately, I can’t install programs directly into our system.

---

<div class="post-metadata">

**Author:** ![John6666](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/john6666/32/27664_2.png) [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [November 15, 2024, 5:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fadvice-on-llms-that-can-be-used-directly-in-python%2F121730%2F4 "2024-11-15T05:01:47Z")

</div>

I guess this is what you mean by a small LLM? If you can use a larger one, your options will increase.

Standard LM, not LLM

> **[Question answering](https://huggingface.co/docs/transformers/tasks/question_answering)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Smaller LLM

> **[Qwen/Qwen2.5-1.5B-Instruct · Hugging Face](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Smaller LLM (gated. need to authorization to use)

> **[google/gemma-2-2b-it · Hugging Face](https://huggingface.co/google/gemma-2-2b-it)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

> **[meta-llama/Llama-3.2-1B-Instruct · Hugging Face](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Models that can be used with the Serverless Inference API (some are gated models)

> **[Models - Hugging Face](https://huggingface.co/models?inference=warm&library=transformers&sort=trending)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.