Replies: 1 comment
-
I have a similar requirement, I want to integrate a Bedrock-imported Qwen2.5-Code model with LiteLLM. Can you please take this up |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I've imported qwen-2.5 coder from huggingface into Bedrock as a custom model.
It's got the following ARN: arn:aws:bedrock:us-west-2::imported-model/
I've tried adding this into LiteLLM proxy using the arn as a custom model name for the bedrock provider, I've tried prefixing with bedrock/, and still no luck.
I notice the model architecture in Bedrock is "Qwen2" - so this might be part of the problem.
Is this a supported scenario, or is the qwen architecture not (yet) supported?
Beta Was this translation helpful? Give feedback.
All reactions