File size: 873 Bytes
a1bf352
 
 
3f42f88
636bc2f
3f42f88
 
 
5d52db8
 
 
1
2
3
4
5
6
7
8
9
10
11
---
license: unknown
---

This is a merge of [LongAlpaca-70B-lora](https://huggingface.co/Yukang/LongAlpaca-70B-lora) into royallb's [Aetheria-L2-70B](https://huggingface.co/royallab/Aetheria-L2-70B), replacing the embed and norm layers as described in the [LongLoRA repo](https://github.com/dvlab-research/LongLoRA), and removing the extra row and pad token so that the vocabularies match.

There is no additional fine-tuning. The resulting model seems to not be broken... you can test whether it is truly the original model + 32K capability (use linear rope scaling 8).

You could also try merging this with other models of longLORA descendency (like [Aurelian](https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16)).

See [this discussion](https://huggingface.co/grimulkan/aurelian-v0.5-70b-rope8-32K-fp16/discussions/2) for how to create merges like these.