Hypernova-2x12B-exp

First time working with Mixture of Experts models

I have not had the time to try this model yet, but it took too much time and resources to not upload it

I am planning on improving this model in the future, so feedback on this model is welcomed

This model is mainly focused on RP and may produce NSFW content

It is a 2x12B model that loads like a 12B but uses both experts somehow

GGUF

Model size

21.1B params

Architecture

llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for theNovaAI/Hypernova-2x12B-exp-GGUF

Base model

Finetuned

Finetuned

Quantized

(3)

this model