Text Generation
Transformers
Safetensors
English
mistral
Not-For-All-Audiences
conversational
text-generation-inference
Inference Endpoints

context

#2
by Ardvark123 - opened

I saw the part about the 3.1 context. But if this is nemo it should be much higher than 8-16k yeah?

Nothing is Real org

I saw the part about the 3.1 context. But if this is nemo it should be much higher than 8-16k yeah?

Even the official Nemo instruct starts breaking down after 16k.

Sign up or log in to comment