E

Erosumika 7B V3 7.1bpw Exl2

Developed by Natkituwu
Erosumika-7B-v3 is a 7.1bpw exl2 quantized language model suitable for running 16k context on GPUs with 8GB VRAM. It was created by fusing multiple models using the DARE TIES method, primarily for entertainment-oriented fictional writing.
Downloads 24
Release Time : 3/26/2024

Model Overview

This model is a fusion of Nitral's Kunocchini-7b, Endevor's InfinityRP-v1-7B, and FlatErosAlpha using the DARE TIES method, mainly for entertainment-oriented fictional writing. Alpaca and ChatML formats work best.

Model Features

Efficient Quantization
7.1bpw exl2 quantized version, ideal for running 16k context on GPUs with 8GB VRAM.
Multi-model Fusion
Fuses multiple models using the DARE TIES method, combining their strengths.
Entertainment-oriented
Primarily for entertainment-oriented fictional writing, supporting Alpaca and ChatML formats.

Model Capabilities

Text Generation
Fictional Writing
Role-playing
Dialogue Generation

Use Cases

Entertainment
Fictional Writing
Used for generating fictional stories and role-playing dialogues.
Generates creative fictional content.
Dialogue Simulation
Simulates character dialogues, suitable for games or entertainment applications.
Generates natural and fluent dialogue content.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase