How long is the longest context length supported?
I'm eagerly utilizing this fantastic model and have noticed its exceptional performance. However, I find the current context length limitation quite restrictive, given that many modern models offer extended context lengths (e.g., up to 32K). Could you kindly provide information on the maximum context length supported by this model and consider implementing higher context length capabilities in future updates?
Given the base model is mistral0.1, I'd presume it would be the same context length as that (8192). However I'd love to see mistral0.2 trained this same way now that the base model is available and get a 32k context length available!
@pootow
thank you for the great feedback . This model has been trained on 2000 has the total context length (1000 input , 1000 output) . In the future iterations we will work towards supporting longer context as well .
But the base model supports 8k context length as
@ElliottDyson
suggested , so technically you can try using upto 8K and benchmark or fine-tune this model with your own data to get the best of longer context and safety features , but this is experimental.
@ElliottDyson our reward starling LM 34B is open feel free run experiments on tuning mistral0.2 and let us know :)