# HF hosted interface API for a finetuned model with LoRA

**URL:** <https://discuss.huggingface.co/t/hf-hosted-interface-api-for-a-finetuned-model-with-lora/37476>\
**Category:** 🤗Transformers\
**Created:** [April 23, 2023, 9:42am UTC](https://discuss.huggingface.co/t/hf-hosted-interface-api-for-a-finetuned-model-with-lora/37476 "2023-04-23T09:42:49Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![sooolee](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sooolee/32/15821_2.png) [@sooolee](https://discuss.huggingface.co/u/sooolee)\
**Post date:** [April 23, 2023, 9:42am UTC](https://discuss.huggingface.co/t/hf-hosted-interface-api-for-a-finetuned-model-with-lora/37476/1 "2023-04-23T09:42:49Z")

</div>

Hi All,

I need a help. When I fine-tuned a flan-t5 model with lora, I got adapter\_config.json and adaptor\_model.bin instead of config.json and pytorch\_model.bin. I used trainer pushing to hub. And if I am understanding correctly, it seems that the hf interface API doesn’t real the adapter\_config because it’s asking for config.json.

How can I make this work? The model works fine generating outputs in notebook. Any idea to fix it?

---

<div class="post-metadata">

**Author:** ![sooolee](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/sooolee/32/15821_2.png) [@sooolee](https://discuss.huggingface.co/u/sooolee)\
**Post date:** [May 2, 2023, 7:29pm UTC](https://discuss.huggingface.co/t/hf-hosted-interface-api-for-a-finetuned-model-with-lora/37476/2 "2023-05-02T19:29:45Z")

</div>

Got an answer. According to HF, “Inference API does not yet support adapter-transformers models for this pipeline type.”

---

<div class="post-metadata">

**Author:** ![Kenkentron](https://avatars.discourse-cdn.com/v4/letter/k/6bbea6/32.png) [@Kenkentron](https://discuss.huggingface.co/u/Kenkentron)\
**Post date:** [January 15, 2024, 10:45pm UTC](https://discuss.huggingface.co/t/hf-hosted-interface-api-for-a-finetuned-model-with-lora/37476/3 "2024-01-15T22:45:31Z")

</div>

Looking at this for example, surely you can host a finetuned model using the Inference API?

> **[juliensimon/llama2-7b-qlora-openassistant-guanaco · Hugging Face](https://huggingface.co/juliensimon/llama2-7b-qlora-openassistant-guanaco)**
>
> We’re on a journey to advance and democratize artificial intelligence through open source and open science.