experimental model based on llama 3.1 trained on roleplay and conversation dataset.

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for scryptiam/Aurora-8B-GGUF

Base model

Finetuned

Quantized

Quantized

(4)

this model