Text Generation
Transformers
NeMo
Safetensors
mistral
text-generation-inference
Inference Endpoints

Context Length

#4
by Sao10K - opened

Hmm, is the decreased context length (8k tokens from model config) a side effect of the training done after pruning? This would have been pretty nice if it retained its long context abilities.

NVIDIA org

This is our plan, to work on longer context. We will update as soon as get results. Hopefully will be able to release the model with 128k context.

pmolchanov changed discussion status to closed

Sign up or log in to comment