# Chat UI With LLAMA 2

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchat-ui-with-llama-2%2F64697%3E%5C
**Category:** Models\
**Created:** [December 5, 2023, 6:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchat-ui-with-llama-2%2F64697 "2023-12-05T18:18:03Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![anon10785030](https://avatars.discourse-cdn.com/v4/letter/a/6f9a4e/32.png) [@anon10785030](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fanon10785030)%5C
**Post date:** [December 5, 2023, 6:18pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchat-ui-with-llama-2%2F64697%2F1 "2023-12-05T18:18:03Z")

</div>

Hi there! I’m interested in the [HuggingChat](http://huggingface.co/chat) user interface available on GitHub. I’m curious about the process of incorporating my own custom model, such as Llama 2, since I prefer not to opt for the pro version. Is it feasible to self-host the model?

---

<div class="post-metadata">

**Author:** ![nielsr](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nielsr/32/39617_2.png) [@nielsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fnielsr)%5C
**Post date:** [May 6, 2024, 10:13am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fchat-ui-with-llama-2%2F64697%2F3 "2024-05-06T10:13:53Z")

</div>

Yes that’s totally feasible!

Hugging Face leverages this to power [HuggingChat](http://hf.co/chat), using TGI as backend and Chat UI as frontend. Refer to the README of Chat ui to use a custom model: [GitHub - huggingface/chat-ui: Open source codebase powering the HuggingChat app](https://github.com/huggingface/chat-ui?tab=readme-ov-file#openai-api-compatible-models).