# On premise model instead of sending over the wire to OpenAI

**URL:** <https://community.deeplearning.ai/t/on-premise-model-instead-of-sending-over-the-wire-to-openai/351167>\
**Category:** ChatGPT Prompt Engineering for Developers\
**Created:** [June 6, 2023, 3:43pm UTC](https://community.deeplearning.ai/t/on-premise-model-instead-of-sending-over-the-wire-to-openai/351167 "2023-06-06T15:43:27Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![cmosguy](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/cmosguy/32/18724_2.png) [@cmosguy](https://community.deeplearning.ai/u/cmosguy)\
**Post date:** [June 6, 2023, 3:43pm UTC](https://community.deeplearning.ai/t/on-premise-model-instead-of-sending-over-the-wire-to-openai/351167/1 "2023-06-06T15:43:27Z")

</div>

Hello -

Corporate firewalls are blocking OpenAI connections because of fears of sending proprietary information off premises.

I was curious what models could theoretically be used in place of the ChatGPT for on premise use. Is there a hugging face model that folks are using that gives reasonable performance?

Thanks!

---

<div class="post-metadata">

**Author:** ![gent.spah](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/gent.spah/32/136423_2.png) [@gent.spah](https://community.deeplearning.ai/u/gent.spah)\
**Post date:** [June 6, 2023, 3:49pm UTC](https://community.deeplearning.ai/t/on-premise-model-instead-of-sending-over-the-wire-to-openai/351167/2 "2023-06-06T15:49:17Z")

</div>

This is what I found in google search.

> **[List of Open Sourced Fine-Tuned Large Language Models (LLM)](https://medium.com/geekculture/list-of-open-sourced-fine-tuned-large-language-models-llm-8d95a2e0dc76)**
>
> An incomplete list of open-sourced fine-tuned Large Language Models (LLM) you can run locally on your computer

---

<div class="post-metadata">

**Author:** ![cmosguy](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/cmosguy/32/18724_2.png) [@cmosguy](https://community.deeplearning.ai/u/cmosguy)\
**Post date:** [June 6, 2023, 4:17pm UTC](https://community.deeplearning.ai/t/on-premise-model-instead-of-sending-over-the-wire-to-openai/351167/3 "2023-06-06T16:17:23Z")

</div>

Thanks I’ll take a look at this and figure out how to hook into langchain.

---

<div class="post-metadata">

**Author:** ![ai\_curious](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/ai_curious/32/128003_2.png) [@ai\_curious](https://community.deeplearning.ai/u/ai_curious)\
**Post date:** [June 6, 2023, 8:54pm UTC](https://community.deeplearning.ai/t/on-premise-model-instead-of-sending-over-the-wire-to-openai/351167/4 "2023-06-06T20:54:35Z")

</div>

This might accelerate your search…an intersection of this list with the ones that are open source…

[https://python.langchain.com/en/latest/modules/models/llms/integrations.html](https://python.langchain.com/en/latest/modules/models/llms/integrations.html)