Would there be a version of model with bigger context size?
#1
by
PrimeD
- opened
Llama 3.1, Command-R, Mistral have models released with longer context lengths already. So I wonder if NemoTron would also come out with longer ones?
Yea, like ~7b 32k context would be great for 8gb vram cards.
Do you know when a GGUF will be available?