#Getting empty response or "I can't help you with that" response on free models
1 messages Β· Page 1 of 1 (latest)
This is usually a ChubAI-side issue, not the model itself. Chub can return empty output or βI canβt help you with thatβ when it struggles with slower responses.
Try this:
- Use the OpenAI base URL format
- Switch to OpenAI Default generation settings
- Try a different site/client if it still happens on Chub
- If the model is busy, wait and retry
Also, free models are limited, so some are not available or may behave differently.
For DeepSeek: only the model IDs listed in /models are supported. If you want, use one of these supported DeepSeek IDs:
deepseek-ai/DeepSeek-V3.1deepseek-ai/DeepSeek-V3.2
If a model isnβt listed on the models page, it isnβt supported.
-# This is an automated response from @crimson vector. While I strive to provide accurate assistance, I may occasionally make mistakes. If you find any inaccuracies or need further clarification, feel free to wait for our community helpers to give you further guidance.
I am using the base URL
I am using the OpenAI Default gen settings
I am sure this isn't an issue on Chub's since I am consistently getting the "I can't help you with that"
messages.
I should also add that I sometimes get a proper responce but it takes multiple re generation and waits.
if anyone is able to help that would be great.
please use cosmosrp v2.1
our models are uncensored
I see