metadata

license: apache-2.0
datasets:
  - FourOhFour/Instruct_Phase
  - FourOhFour/RP_Phase
  - adamo1139/toxic-dpo-natural-v4
  - nbeerbower/Purpura-DPO
  - nbeerbower/Arkhaios-DPO
  - Chaser-cz/DPO_Pairs-Roleplay-NSFW
  - FourOhFour/Human_DPO_Emojis_Removed_Shortened
  - flammenai/Date-DPO-NoAsterisks
  - antiven0m/physical-reasoning-dpo
language:
  - en
base_model:
  - google/gemma-2-9b

Aura-9B

Introduction

Aura-9B is a state of the art dedicated roleplaying model designed to fulfill your every desire.

This finetune started its life as a ChatML modified Gemma 2 9B base model. It has seen several hundreds of millions of tokens of instruction and roleplaying finetuning. A specialized direct preference optimization was also performed to give Aura a unique output style.

Developed by Aura Industries, with contributions from Anthracite Org.

Model Details

Model Name: Aura-9B
Base Model: google/gemma-2-9b
Model Type: Chat Completions
Prompt Format: ChatML
License: Apache-2.0
Language: English
Max Context: 8,192 tokens

License

This model is licensed under the Apache 2.0 License.

Open LLM Leaderboard Evaluation Results

Awaiting results...