---
base_model:
- 152334H/miqu-1-70b-sf
- NeverSleep/MiquMaid-v1-70B
- Sao10K/WinterGoddess-1.4x-70B-L2
library_name: transformers
tags:
- mergekit
- merge
---
# aranea-ancilla-116b-v1.0
**aka MiquMaid-v1-70B + interleaved WinterGoddess-1.4x-70B-L2**

![image/png](https://cdn-lfs-us-1.huggingface.co/repos/b8/27/b827a8b909d8601d579d04dbf9524d5437b2d132ff2b518a18ec16e6c1c21d4d/e5134400ec8efe9313c010654f4385f42474d2ce77d0bd235849f95d683c2e35?response-content-disposition=inline%3B+filename*%3DUTF-8%27%27aranea-ancilla.png%3B+filename%3D%22aranea-ancilla.png%22%3B&response-content-type=image%2Fpng&Expires=1710576329&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTcxMDU3NjMyOX19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2RuLWxmcy11cy0xLmh1Z2dpbmdmYWNlLmNvL3JlcG9zL2I4LzI3L2I4MjdhOGI5MDlkODYwMWQ1NzlkMDRkYmY5NTI0ZDU0MzdiMmQxMzJmZjJiNTE4YTE4ZWMxNmU2YzFjMjFkNGQvZTUxMzQ0MDBlYzhlZmU5MzEzYzAxMDY1NGY0Mzg1ZjQyNDc0ZDJjZTc3ZDBiZDIzNTg0OWY5NWQ2ODNjMmUzNT9yZXNwb25zZS1jb250ZW50LWRpc3Bvc2l0aW9uPSomcmVzcG9uc2UtY29udGVudC10eXBlPSoifV19&Signature=auQEMmxbglMR1BrezeeWnAMHrLQO5kprIlnyk1g%7EC75fXRzEuIlZUqmBPGy7mQDDXi5Iax8ibVzLUoWgzKC5tTPwGkHzyRRWAYUC5omiM27dpOMp4qqKra%7EDYktIq21XJigrfoqxqUUFUxOi9QQRBXsa2oEhcy3FT-cW6pCZud%7EwI151cCZqMzwKQ6xfoeVX326xh5I2qTaSqdwK7%7EUzq6uV5g2IGaLYrfulGtHfGnit%7E-02dauC-GoF6moCRKcCrRvVcyZLDvBRYoqVOhh6t8RKr6hkK36KJ%7EKADT-dfTjA3PaPsb%7EO3m426trPXqVPRnkJE7TEbzEvTbyyyk-xNg__&Key-Pair-Id=KCD77M1F0VK2B)

A [mergekit](https://github.com/arcee-ai/mergekit) frankenmerge based on [NeverSleep/MiquMaid-v1-70B](https://huggingface.co/NeverSleep/MiquMaid-v1-70B) with interleaved layers of [Sao10K/WinterGoddess-1.4x-70B-L2](https://huggingface.co/Sao10K/WinterGoddess-1.4x-70B-L2).  
This was the top performing model from a series of merge experiments to create a highly coherant creative writing model. 

Tests consisted of a series of private benchmarks and manual comparisons. A number of different base models, interleave models and layer offsets were compared.

- Usable context ~32768
- Recommended context ~16384

Non frankenstein miqu-1 finetunes generally outperform their frankenstein counterparts at very long contexts due to coherency loss.  
As a rough suggestion I might suggest swapping out to either [NeverSleep/MiquMaid-v1-70B](https://huggingface.co/NeverSleep/MiquMaid-v1-70B) or [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) after 16k context.

Layers: 136

### License

No license. Component models based on the [Mistral AI Miqu-1](https://huggingface.co/miqudev/miqu-1-70b/tree/main) llama2 finetune that was released without license.

### Interesting observations from benchmarking

- 10 layer interleave stride with a 20 layer interleave width consistently outperformed alternatives combinations.
- Offsetting the interleaved model's first set of layers generally improved coherency. [14-30] reliably beat the [10-30] mergekit slice configuration for various combinations of models.
- Quality of resulting merges can vary wildly. Whilst a merge of two strong models tends to produce a strong frankenstein model, this rule does not always hold true.

### Quantizations

Exllamav2 quants will be available when bandwidth permits.