This is a finetune of NousResearch/Yarn-Llama-2-13b-64k. This starting point is Llama-2-13b with additional pretraining done with YaRN scaling applied to RoPE to extend the useful context length to 64k tokens. Starting with this model, I performed instruction tuning with Jon Durbin's Airoboros 2.1 dataset, with same scaling approach applied.

This is a (merged) QLoRA fine-tune (rank 64).

The finetune was performed with 1x RTX 6000 Ada (~18 hours).

For full model card, including benchmarks, see the model card of the fp16 merged model