I love the HF inference providers, but now ran into a question: Is it possible to get access to the model’s processor output as well via the API? My specific use-case is with Qwen2.5-VL. I ask the model to perform localization tasks on document images. I ask the model to find bounding box coordina…

If it were a Dedicated Endpoint that you could maintain yourself, you could change the return value by just rewriting handler.py , but since you are using the Inference Provider, that part is a black box. Therefore, as you suggested, mimicking the processing that is likely being done internally is …

Inference providers: Access to processor data?

Inference Endpoints on the Hub

system Closed July 29, 2025, 12:50pm 3

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.

Topic		Replies	Views
How to have custom output size for inference API Inference Endpoints on the Hub	4	1321	February 16, 2023
PRO Plan and for running huge models on free inference api? Beginners	1	1807	May 15, 2023
Accessing model through Inference Endpoint Beginners	2	286	June 3, 2024
`width` and `height` not working on Inference API Inference Endpoints on the Hub	2	443	August 9, 2023
Inference Api ( serverless ) Endpoint Inference Endpoints on the Hub	0	456	April 24, 2024

Inference providers: Access to processor data?

Related topics